ReSolve 12 Days of Investment Wisdom

Disclaimer:00:42Mike Philbrick, Adam Butler, Rodrigo Gordillo, and Jason Russell are principals at ReSolve Asset Management. Due to industry regulations they will not discuss any of ReSolve’s funds while on this podcast. All opinions expressed by the principals are solely their own opinion and do not express the opinion of ReSolve Asset Management. This podcast is for information purposes only and should not be relied upon as a basis for investment decisions. For more information visit investresolve.com

Mike:01:10Welcome back and today, we have episode 11. We have a new guest with us, not a guest, a new host. As you may know, ReSolve underwent an amalgamation with another company called Acorn Global Investments in July of this year and with that came a full team, with a breadth of knowledge and depth of knowledge in the managed futures arena, the likes that I think is unrivaled and with us today is Jason Russell and let me just take a moment to brag on Jason a little bit.

Jason:01:43Hey Mike.

Mike:01:44How are ya? Good to have ya here.

Jason:01:46Thank you, thank you.

Mike:01:48So, we wanted to introduce Jason, first of all, and then get him onto the podcast and onto our other media sources so everyone can get to know him and get to the level of expertise that lies within ReSolve so, Jason’s been in the, in the industry for 25 years plus, I don’t want to tell them your age. You’ve been handling managed futures and managed futures portfolios for 15 years or so-

Jason:02:14Yup.

Mike:02:15And we’ve been working quite closely with Acorn over the years and this year just seemed to be such a synergistic opportunity to bring the two organizations together and something we say around here a lot is to get better together, and this has been truly a wonderful experience over the last six months in combining the teams and looking forward to a super exciting 2019. Adam, what are your thoughts?

Adam:02:40Yeah, amen to that, you know, it was great because we got into running our strategies in futures markets a couple of years ago, uh, there’s a huge amount of operational overhead and a, a steep learning curve to get that going and it was just really great to have been able to tap Jason and his team’s expertise as we went forward with that and then, just a full integration made so much sense at this point in time, as we really begin to focus on future strategies, so uh, great to have Jason here.

Jason:03:09I’m thrilled and the whole team is thrilled, you know, we’ve been working so closely together for so long. It just made an immense amount of sense and now that we’re on the other side, uh, you know, six months through it, it makes even more sense, as we recognize all the things we were doing similarly and the, the areas in which we really help support each other so, this has been fantastic and you know, from a strategy standpoint, what we bring from the Acorn side and the ReSolve side is, is, there’s a similar DNA, yet we’re very different in many other ways that I think really, really complements each other.

Mike:03:45Agreed, and with that, we’re going to jump into today’s topic, which is the idea of, uh, diversification and what most novice investors miss about trend following and this is an article that’s on our blog and we would encourage you to, uh, read this or as you, either post pre this podcast cause we’re gonna dig in here a little bit and it’s great to have someone with 15 years of hands on, trend following experience dealing with futures in our midst as well, so I think the one thing that, that’s covered in this article and, and something that I think happens to everyone as they start this journey down the path of, of trend following is this realization whether it’s through Jeremy Siegel’s work in, uh, what is it called? “Stocks for the Long Run”, right, yeah? So his work at the 200 day moving average or Meb Faber’s work on the 10 month moving average and there’s a, there’s a-

Jason:04:36Mike Covel’s book on trend following-

Mike:04:38Exactly.

Jason:04:39There’s been a long history of, of these people eventually come across the idea of trend following.

Mike:04:43Right.

Jason:04:44The natural place to start for most people is the conventional asset they’re all used to investing in, which is stocks.

Mike:04:49Exactly, and then they, then they tend to go with the one conventional indicator that they know, which is the 200 day-

Jason:04:56Moving average. Yup.

Mike:04:58Moving average and I think, I think Adam, you do a great job of really sort of bringing this to life so why don’t, why don’t you walk us through sort of the start of this.

Adam:05:06The motivation for this article was really rooted in conversations that we have over and over again with advisors and investors who have discovered that they really don’t like all the major ups and downs that are involved in equity investing and they come across papers or some articles that show the power of trend following on the S&P or the Dow, for example, and how, if you go back over the very long-term, the last 100 years or so, that a, over the long-term, this sort of simple trend following strategy can produce approximately the same, long-term return, but with much smaller draw downs and so, they naturally say well, you know, I really understand the S&P 500, I get it, I’m used to it, and so now I’m just going to add this really simple rule to put it in play and expect that I’m going to just avoid the draw downs and get all the upside and it’s just, it’s not the way that works and you know, we spent quite a bit of time in the last, you know, one of the episodes a couple of times ago, talking about the power of ensembles and how it’s really important to, to integrate a variety of different systems on a variety of different markets. That’s the real power of systematic investing and so that the objective of this article was really just bring that to life.

Mike06:22Perfect, and let’s, let’s lay it out then. Let’s just dig into the numbers that are in the article, so that if you hadn’t listened to episode 9, where we cover ensemble methods and the idea of getting more robust universes and more robust ways of looking at, you know, whether it’s a lookback, whatever please, go back and have, have a listen to that, uh, because this is a little bit more in-depth of an actual example, so if we take the classic 200 day moving average, look at 15 stock indices across the world, what we find is the, uh, median Sharpe ratio is about .45 on looking at the 200 day, uh, getting out when you’re below, getting in when you’re above-

Jason:07:01Yeah, I just wanna just make that really clear here cause maybe, just to be super clear, ultimately, when the trend is up, we’re long, when the trend is, uh, when the price is below the 200 day, you’re not long.

Adam:07:13Right, you’re just flat.

Jason:07:14You’re not short, you’re just out and there are benefits to that as Adam said, for sure.

Mike:07:18And so, if we look at that, we’ve got sort of the median as .45, on the Sharpe ratio, um, but there’s a huge dispersion here, right, the, the worst compounding rate was uh, only doubling your money over the time period with the TOPEX versus having 16 times your initial investment in Finland. And so you have this huge opportunity for good luck or bad luck, which we covered in podcast 9, and what we, we don’t want is luck. I don’t want, we don’t want good luck, we don’t want bad luck. We kind of want to be somewhere in the middle because we can’t know in advance which one of these markets is going to outperform in the future. We know what happened in the past, but what does that really tell us? But what’s so interesting, is if you take a diversified approach and you consider all 15 of these equity indices and you operate the portfolio looking at all 15, you get a Sharpe ratio of .76, which is a diversification bonus of, of .31 Sharpe ratio points, which is a 65 percent increase in Sharpe ratio, without having to rely on luck.

Jason:08:29Yup, not making a guess.

Mike:08:31And so, if you think about that, only one market actually outperforms that diversified basket so you would’ve had to pick the market, you would have had to pick the, you would’ve had to pick Finland.

Jason:08:43Yup. One market out of 15.

Mike:08:45And who, everyone here put your hands up, but I know if you’re driving, keep both hands on your wheel, but, would you have picked Finland? Hahaha, at the beginning of this and said, I know most people would pick the S&P, which is about in the middle, if you look at the article, but I’m not sure that a lot of people would have picked Finland, and if you don’t have to pick Finland, why would you?

Adam:09:04I just think it’s just such, it’s such, it’s, it’s such incredible magic. You’ve got, you know, some strategies as part of the 15 that turned a dollar into two dollars over 35 years. You’ve got other strategies that turned a dollar into 16 dollars. Most of them, somewhere in the middle, the S&P, very much right smack dab in the middle, from a trend following perspective, but if you put them all together, naively, you just hold them all in equal weight, run all the strategies together, that ensemble outperforms 93 percent of all of the individual strategies and only one strategy of the 15 over that entire horizon produced comparable performance. I mean, it’s pretty amazing that you, you, you don’t have to take a stand, you don’t have to make a guess, you don’t have to predict in advance, you can just, trade them all and get a better result than you’d get from basically knowing the future in advance.

Mike:09:56Yeah, and this is just the first step in sort of the equity complex in understanding, uh, how ensemble methods can, can benefit you because, you know, we’re still only looking at the 200 day.

Jason:10:07Yeah, exactly. You can look at all kinds of parameters, from, from way down to zero to 500, and everything in between, as well, so.

Mike:10:16And now, now, let’s jump in to adding other asset classes, so that was the equity complex and you, one would think that, well first of all, we wanna observe is, across the bond complex, across the currency complex, across the commodity complex, do we observe the same sort of improvement by, uh, by looking across a broad swath of those underlying indices within those complexes versus just the single market itself. And what we see is across the board, this improvement is pervasive. It does vary, so just a, I’ll give us the numbers, just for those who are not looking at the article, but in bonds you get a median, uh, Sharpe ratio of .63, a diversification benefit of .26, if you pursue the ensemble method, giving total, you know, a total Sharpe of .89 across the diversified universe. Currency goes from median of .31 up to a Sharpe ratio of .41, so a diversification bonus of .1-

Jason:11:17And I’ll take the numbers, if I can.

Mike:11:18Yeah, absolutely. Jump in.

Jason:11:20Sure, absolutely, cause, uh, speaking from all the experience here, but 24 is the median with commodities and a, a huge diversification bonus to get up to 55, so a diversification bonus of 31 and you know, really, this one to me, it makes the most intuitive sense as to why you’re going to see that large diversification bonus, cause here we’re talking about markets like coffee, live cattle, cotton, crude oil; massively different and diverse markets. Bonds, as different as they can be, you’re basically, uh, diversifying by government regimes, corporate regimes, geography, etc. but the fundamental nature of the instrument, a fixed coupon and maturity date, uh, is very, very, very, very similar so, huge benefit in the commodity sector.

Adam:12:03It’s a really good point, because, you know, bonds, despite the fact that there were 7 or 8 different bond indices, they all are fairly highly correlated. Bonds are fairly highly correlated with one another, even around the world, even more so than, than global equity indexes are and then currencies, they’re are all currency crosses vis-a-vis the U.S. dollar and so, they tend to be, they said, they sort of cluster into commodity groups and the Yen is sort of its own cluster, but you get way less diversity in bonds and in currencies than you typically do in commodities for the reasons that you outlined and that shows up in terms of the diversification bonus.

Jason:12:40And the interesting thing, one, just one note on currencies, particularly in the last 10 years and after, the, the credit crisis, the coordination among central banks was very, very high and historically, if you looked further back, you know, when I was doing my testing way back before the credit crisis, a decade before, the currency sector actually, uh, would have exhibited much higher diversification bonus and I wouldn’t be surprised if, if going forward we actually see that diversification bonus increase, as we’re already seeing a bit of a decoupling of monetary policies around the world right now.

Mike:13:13Yeah, no, very good point.

Adam:13:14You should keep going Jason cause you’ve got the most experience in this, but I mean, um, as you sort of close a loop on this concept, I mean the real power comes when you combine all of these different sectors, together, right?

Jason:13:27Right. Absolutely, the biggest benefit in trend following or managed futures or this approach, is really just the massive difference in markets and having a, as broad a market universe as you can and there’s some really interesting markets when you go beyond stocks and bonds; things like carbon emissions, things like, uh, Malaysian palm oil, there can be a really obscure, highly liquid markets, rubber. Try to go through a day without having your tires on your car or rubber on the end of your toothbrush when you’re, uh, picking your teeth, it’s amazing. Rubber is absolutely everywhere, it’s a massively liquid cash market and there’s a, there’s a liquid futures market as well and there’s incredible liquidity and, and to add that into the mix really, just truly adds something very, very different.

Mike:14:15Just to add to that point, this is an amazing thing as we, as we’ve expanded our business into the futures arena and as I explain to people, you know, how ReSolve is evolving and growing and generally, the individual investor and the individual person does not understand that the futures market is the basis of everything that comes into production.

Jason:14:38Mm-hmm.

Mike:14:41If you look at the shirt you’re wearing, the shoes you have on, at some point, the production materials in those things, were a futures contract.

Jason:14:48Yup.

Mike:14:50They were sold from a producer to a speculator to manage the volatility of production. And it’s just amazing to me that this fundamental basis of finance is often, sort of, you know, marginally are not well understood by the investing public, generally.

Jason:15:03Yeah, just, just consider Starbucks. You’ve got investors and speculators and owners, uh, that’s about it. Look at coffee, you’ve got growers, you’ve got transporters, you’ve got roasters, you’ve got the retail side, and all the various types of buyers. All of those people are willing to engage in the coffee market, regardless of what’s going on in the stock market, they have to and in the credit crisis, there were a whole lot of, of these markets that, that maintained liquidity without missing a beat, whereas government bonds off the run, saw massive spreads and liquidity pockets that were really hard to believe, but unleaded gas, crude oil, coffee, cotton, all of these things, there’s a whole world out there, they don’t give a hoot about what’s going on in the equity market. They wanna make t-shirts, they wanna make coffee, they wanna make gas, and that’s a really important benefit and if you’re engaging in a strategy like this, one of the implied things to understand is there is an exit and so, if you want to exit and you want to count on the ability to exit, then the first thing you need to look at is liquidity.

Mike:16:13I’m going to bring this around because we’re going to get a little bit long on this episode but I love it, first and foremost, let’s, let’s continue discussion, so as we’ve covered in the first eight episodes, we talked about this diversity of opportunity, the diversity of the bets we might be able to pursue in a portfolio and how that diversity can offer extremely attractive benefits to a portfolio from the, from the perspective of the actual realized risk adjust and returns and what you just talked about in that point of the diverse opportunities in the commodity world, I mean that is something that we wanna, we wanna take advantage of and so…

Just continuing on the article, uh, if we get that all markets together, so now we’re gonna take that equity complex, that bond complex, the currency complex, the commodity complex, and we’re going to go through this same process, what we find is that the median market, if you’re going to trend follow, is gonna give you a Sharpe of .3. If you combine them all together, using this very, sort of simple process of trend following, you get a Sharpe ratio of 1.14. That’s a diversification bonus of 84 basis points, two and a half times, almost, the risk adjusted returns of using just one area of ensemble, as in the asset class, the underlying individual security, not diversifying across multiple look backs and portfolio optimizations and what not, just this one first step-

Jason:17:40And even if you cut that diversification benefit in half, that remains very impressive. That’s a big number, for sure.

Adam:17:47The big, attractive take away, right, is that in markets, the best you can hope for is a small sustainable edge, you know, these Sharpe ratios and the range of .3 and .4, this is exactly what you should expect from the strongest edges in markets. So, the goal should not be, let’s go out and find a really, really large edge, because the problem is those large edges they tend to be easy to find and they tend to be fleeting, they go, they are easily arbitraged away. The most sustainable edges, due to structural or behavioral inefficiencies in markets are gonna produce these types of .3, .4 Sharpe ratios. The only way to produce really strong, persistent long-term performances by combining a large number of diverse, weak strategies and that, this is just an example of, of how that works. Right, isolating the one individual market, it’s just not gonna get you there, you’re, you’re only getting a fraction of the opportunity that’s available to you. It’s the magic is in combining many diverse, even fairly weak, strategies together and when you do that, you know, it’s, it’s magical just what you can achieve.

Mike:19:05Well guys, Jason, amazing having you on the podcast.

Jason:19:07Thank you. It was my pleasure. Real fun.

Michael P.:19:10Glad to hear your, your voice echoing into the podcastophere, always a pleasure with you Mr. Butler and that wraps up day 11. Day 12 coming our way. And looking forward to wrapping this up and um, thanks gentleman.

Jason:19:25Great, thanks Mike.

Adam:19:26Thanks guys.

Rodrigo: 19:27Thank you for listening to our 12 days of Investment Wisdom mini-series. You will find all the information we highlighted in this episode in the show notes @investresolve.com/12 days. You can also learn more about ReSolve’s approach to investing by going to our website and research blog at investresolve.com, where you will find over 200 articles that cover a wide array of important topics in the area of investing. We also encourage you to engage with the whole team on Twitter by searching the handle @investresolve and following Adam, Mike and myself. If you’re really enjoying this series, please take the time to share us with your friends through email, social media, and if you really learned something new and believe that our series would be helpful to others, we would be incredibly grateful if you could leave us a review on iTunes. Thanks again and see you next time.

Disclaimer:00:42Mike Philbrick, Adam Butler, Rodrigo Gordillo, and Jason Russell are principals at ReSolve Asset Management. Due to industry regulations they will not discuss any of ReSolve’s funds while on this podcast. All opinions expressed by the principals are solely their own opinion and do not express the opinion of ReSolve Asset Management. This podcast is for information purposes only and should not be relied upon as a basis for investment decisions. For more information visit investresolve.com

Mike:01:10Welcome back, hot off the back testing and ensemble methods and nuance differences in those areas. Make for interesting differences in strategies. We now head to today’s all about “The Optimization Machine …”, one of our recent research papers that has also attracted a tremendous amount of attention and so today we’re going to ah, be chatting about that.

Rodrigo:01:40No, that’s exactly right. And what we want to talk about today is really shine a light on the fact that the weighting scheme is just as important, if not more important than the strategies that you put in place. You can’t simply use an equal weight methodology without understanding that, that is a very active decision that is affecting the Sharpe ratio that you’re going to get in your portfolio, the return per unit of risk that you’re going to get in a new portfolio.

And so today we’re gonna kind of walk you through some of the more common ways of weighting that many people use because they’re easy, and then see if we can test the assumptions by which we came to those weighting schemes and then try to improve on them by looking at real empirical data and what it says to us to see if we can do a better job at that very, very important part of the equation. So why don’t we, uh, let our CIO take over from here and walk us through a little bit of the paper and some of those weighting schemes.

Adam:02:30This is going to be a lot of fun today. We’re going to really sacrifice some sacred cows. By habit or convention, the reality is most investors default to just a handful of heuristic methods for portfolio construction. You kind of have market cap weighting, maybe equal weighting. You’ve got convention weighting, right? Which is kind of, well this is what everybody else does, so this is what I’m going to do too. Think about your kind of 60, 40 portfolio for example. And then you’ve got conviction weighting, which is a lot of conventional active managers, mutual fund managers, you know, they’ve got a list of stocks that they like, they liked certain stocks more than others, the stocks you’d like to get more weight in the portfolio and vice versa. Right?

So there really are four different traditional weighting methods and, and what we’re going to challenge today is the assumption that any of those weighting methods really hold water most of the time. And I think a natural place to start is by looking at some of the assumptions that we make about what investors would prefer in terms of the character of their portfolio and their investment experience. And so I think we should, we should start by laying a few ground rules. Number one, that investors, when they’re asked in a calm state, when they’re being thoughtful and reflecting on what they want from their financial future and their objectives, will say that they would prefer to have higher returns.

So a higher mean expected return while minimizing risk or minimizing the distribution of terminal wealth or you know, the, the money that they have at the end or that they use to fund whatever their financial liabilities are. And so financial professionals, they call that set of preferences Mean Variance Optimization, right? You’re trying to maximize your mean expected return while minimizing your expected risk, your volatility, which then leads, volatility directly impacts the dispersion of terminal outcomes. Right? So this is Mean Variance Optimization, and we’re going to actually make, another assumption as well.

And that is that typically the reason why investors default to these heuristic methods of portfolio construction is because they want to avoid having to make active views about the investments under consideration in their portfolio, right? They, they sort of intuitively understand or have been taught to believe, that it’s really hard to estimate relative returns. It’s hard to estimate risks, hard to estimate correlations, and so they want to construct portfolios in ways that they think obviate that necessity to express those active views. Right?

So, so two basic assumptions. Number one, people are mean variance optimizers, they want maximum return for minimum risk and secondly they want to minimize the degree to which they’ve got to calculate or be precise about the active relative views on returns or risks or correlations in the portfolio. So if we can kinda start at that baseline then I think there’s a really neat arc of conversation that builds on that.

Mike:05:51Is the market cap, is part of market cap the function of the wisdom of crowds to some extent. How does that play into the use of market cap?

Adam:06:00It is for sure. I mean that’s a really good point. So I think it’s helpful to go back and revisit the foundations of the CAPM, the capital asset pricing model, which is the model that leads to the conclusion that the market cap weighted portfolio is mean variance optimal. That it will produce ex ante is expected to produce the maximum amount of return per unit of risk, and the CAPM goes back to the 1960s, you’ve got Sharpe and Trainer and Markowitz and all the, the grandfathers of financial theory, all producing these papers and all thinking about this concept of market efficiency and they decided that the market was efficient when it expresses the views of all market participants.

And then they realized that the portfolio that that expresses these views in equilibrium is, is the market cap weighted portfolio because it allows all investors to invest in all assets and whatever value they place on those assets. The relative of those values is the market cap weighted portfolio.

Mike:07:07Right.

And it’s, its portfolio everyone could hold?

Adam:07:09It’s the portfolio everybody by definition does hold.

Mike:07:10Sure.

Adam:07:13And therefore obviously the portfolio that everybody can hold. Exactly. And so it has a very large amount of capacity, in fact the maximum amount of capacity of any portfolio, and so going back and sort of revisiting some of the mathematical assumptions for CAPM, and so yes, it, it assumes market efficiency in so far as individual investors have priced all global assets at equilibrium, but it also, in order for it to be mean variance optimal, it also assumes that every investment will produce returns in proportion to the non-diversifiable risk relative to the market portfolio, and so if you sort of, if you think about CAPM the way that most people think about CAPM these days, which is in the context of a stock portfolio and specifically let’s just use U.S. stocks as, as a sandbox for discussion.

Then what it says is that the, the CAPM says that an individual stock should produce returns broadly commensurate with that stock’s beta to the market, and so in order for just to just, just to close the loop on this, if CAPM is true and therefore if a market cap portfolio is truly mean variance optimal, then we should expect to see empirically that assets have historically had a return that is a linear function of that the stocks beta.

Rodrigo:08:48The higher the beta the higher the return.

Adam:08:50Higher beta equals higher return. That’s what we need to see in order for CAPM to be legitimate and in order for the market cap weighted portfolio to be mean variance optimal.

Rodrigo:09:02The pervasive meme of investing across the planet, if I take more risk, I’m going to get better return in my equity selection.

Mike:09:10And then of course you have the low vol phenomena that just absolutely stands…

Adam:09:18Exactly. And that provides the first clue I think.

It’s sort of the next phase of understanding in our portfolio optimization framework because, and this is not a new concept, it goes all the way back. Of course, Hogan produced research in the 80s that showed that stocks do not produce returns commensurate with their volatility. If anything, the relationship is inverted on a multi period model, but the seminal research from Fama and French 1992, The Cross Section of Stock Returns, table one in that paper shows, returns of stocks historically sorted on beta and size, and so what they did is they divided stocks every month into buckets based on the stock’s beta.

So 10 buckets. You’ve got very low Beta stocks in bucket one, very high Beta stocks in bucket 10 and what they, what they showed is that after controlling for size, that the arithmetic returns to stocks in beta decile one, so low beta stocks are exactly the same, or at least statistically indistinguishable from the returns to stocks in the highest beta decile, and it’s basically true across all deciles. All deciles sorted on beta ended up having the same return. In other words, what they showed was that there is no relationship between beta risk and stock returns, which guess what, totally invalidates the CAPM and therefore leads to the conclusion that the market cap weighted portfolio is profoundly mean variance sub optimal. You can get better returns for any unit of risk by investing in a portfolio that is different from the cap weighted portfolio.

Mike:11:08Let me summarize that. So if the market cap portfolio is mean variance optimal, that would mean if that were the result, that would mean that stocks would have returns that are, that are proportional to their market beta. So the higher the beta, the higher the return. What we observed through time and what has become very popular low vol investing recently as an example of this standing in the face of that, is that the return per unit of beta is the same across the different betas.

Adam:11:40Exactly.

Mike:11:42And so now we have this challenge where we have portfolios that, I mean obviously the largest allocation to equity portfolios probably globally and in any geographic region is a market cap weighted portfolio. We’d probably look up some data on that. Probably next is equal weight and then maybe you might get low vol or min vol type portfolios creeping onto the radar, but they would be a very, very small percentage of …

Rodrigo:12:05Maximum diversification.

Adam:12:06Do you think? I mean I would, I would think that the after market cap weight, probably the next most prevalent weighting scheme would be conviction weight. You still have all of these discretionary active mutual funds out there that are still forming portfolios in the classic way of saying my discretionary call is that stock A is more attractive than stock B and therefore I’m going to give it a higher weighting in the portfolio. Basically ignoring any information about relative volatilities, or the correlation of that asset with or that investment with other securities in the portfolio.

Rodrigo:12:42Right. But I mean, the reason it’s just if you’re building a multi billion dollar firm, then you want market cap weight to be the most optimal portfolio because that’s where you can fit the most amount of money in.

Mike:12:53Well of course this …

Rodrigo:12:55This is this, this is why that dominates. And, and this is why. If everybody believes in which a lot of people still do, then it’s going to dominate the zeitgeist and the vast swaths of money will want to be in it.

Mike:13:10Who has the most money to market these various things? The largest companies, what are they going to produce? Are they going to produce highly focused portfolios or are they’re going to use sort of broader rules that allow for a lot of capacity?

Rodrigo:13:23Exactly.

Capacity rules here in the business.

Adam:13:25It’s true, but. But when you think about the fact that the margins on these cap weighted products are essentially going to zero, then the revenue for these asset management firms has got to come from models that are different than market cap weight because there’s basically, there’s no margin anymore in market cap weighted, market cap weighted products. The good news is that there are lots of very good theoretical and empirical reasons to deviate from market cap weight as we’ve, as we just touched on. Right, but I mean, just, just to close the loop on this, like, like Rodrigo said, if you’re CalPERS, if you’re CalPERS, and you are the market, then you are seeking the most liquid, most high capacity access point for exposure to whatever the risk premia is you’re seeking, whether it’s U.S. stocks or global stocks or global bonds.

It needs to be market cap weighted. It has to be. That’s the only way you can get the capacity you need. If you don’t have portfolio agility, if you don’t have mandate flexibility, then you’re constrained to market cap weighting. Fortunately, most of the people that we talked to, the advisors, the individual investors, the small, the medium sized institutions don’t have those constraints and therefore they have an opportunity to produce, we think very substantially more efficient exposures to the global sources of return that everybody’s after.

Mike:14:45Oh yeah. Let’s dive into that because that that is a, a lot of where this paper really digs in deep, and you know, I think, I think the reality is that, that the views, that you are expressing views about the various volatilities, correlations and expected returns of the individual holdings in your portfolio, you are expressing those views whether you’re aware of that or not. They are being expressed, and I think what this, this paper helps to uncover, shed light on is the fact that here is what the assumptions that you’re making in your portfolio.

So an equal weight assumption for example means that you kind of know nothing, right? I, I don’t know volatilities, I don’t know, correlations, I don’t know, expected returns and as such I’m going to buy an equal weight portfolio. And in certain circumstances that’s actually a really good idea. Like if you are buying a sector ETF where you have a very small sector of whatever, telecom, technology, these are going to have very similar reactions to news that comes into the sector and so.

Rodrigo:15:53Highly correlated.

Mike:15:55And they’re highly correlated. So assuming you knew nothing about correlations is, is not. It doesn’t hurt you. The volatility, probably going to be somewhat similar, what the expected return might be going forward from the smallest companies in a particular, um sector to the largest, you know, you’re, you’re going to actually benefit from, from having more small company exposure. So it’s interesting that in that context that, that’s not a bad assumption, but could you do it better? Probably. And so, yeah. Let’s, let’s, let’s jump off from there.

Adam:16:20Yeah, great, great point. I mean it’s, it’s absolutely worthwhile spending one more moment on equal weighting because as you say, equal weighting expresses no views, but it also sort of expresses, it does express a very strong set of views as well, because it expresses the view that all assets have or all investments have the same expected return.

Mike:16:43Yeah.

Adam:16:44It expresses the view they all have the same risk, that they all have the same correlations.

Mike:16:48Right. Right. So no view is, is a view, right?

Adam:16:52Exactly.

Mike:16:54Like it’s a very strong view.

Adam:16:55Its a very strong view.

Mike:16:56Yeah. No, agreed. And I did. Yeah. That’s, that’s a very crucial point. That no view is a very strong view.

Rodrigo:17:01It’s an inadvertent view, right?

Mike:17:03Yeah.

Rodrigo:17:03A lot of people think, well, I don’t know if I’m not going to do anything.

Mike:17:05Right.

Rodrigo:17:06You actually do it, there is no doing anything.

Mike:17:08Right and now, and now the universe selection, right? So my example was a sector, okay, well that’s the universe selection. So that’s, that’s particularly relevant. If we take another universe, which is 500 stocks and one bond, and we equal weight, that bond is going to have no opportunity to provide any diversification. Let’s call it a government bond. But if we were to say we have 500 stocks and one bond, and we’re going to do an equal risk contribution portfolio, that one bond’s going to have a pretty massive holding within that 501 security portfolio.

Rodrigo:17:47Yeah. So that, that’s just saying, uh, so equal weight will, you will get one, one 500th of an allocation to that bond.

Mike:17:54Yeah.

Rodrigo:17:55When you don’t care about the line items, but care about creating balance in the portfolio by understanding the correlations. Assuming you can, you can estimate the correlation is relatively well, then you will have it for from an equal risk contribution perspective of bond that has lower volatility and non correlated, be a dominant position in that portfolio, right? So which is better? If you are trying to create, if your goal is to maximize your return per unit of risk, then there are other weighting schemes that we need to consider, and we have to look at the data in order to come to, to assumptions and conclusions about our assumptions and whether they’re real or not, whether the assumption that we can’t foresee or estimate correlations correctly is correct.

Whether we can’t estimate volatility is correct, and we think that we can do all of those relatively well and if you can do all of those relatively well when the whole plethora of optimization schemes come to fruition that, that we can take advantage of to maximize their potential unit of risk.

Adam:18:54Exactly.

Mike:18:55And the funny thing is that the mean is the hardest one. Like the expected return is the hardest one to estimate and is often where everyone starts, well, why am I picking this one stock? Because I think the return is going to be the best return, but you should have the lowest confidence.

Rodrigo:19:14I love that fact.

The conclusion is that all, all equities provide the same return because then it means I know what I can focus on, and we do see, the evidence does point to the fact that we can do a very good job at estimating correlations. You can do a very good job at estimating volatilities. And so, uh, why don’t you walk us through some of the.

Mike:19:30Walks us through. Yeah. Walk us through your favorite portfolio Adam.

Adam:19:34Just to be clear, this is not my favorite portfolio, but it is a portfolio that I like a lot for equities.

Mike:19:38Hold on. Is it not your favorite equity portfolio?

Adam:19:40Yes. Unconditionally, you…

Mike:19:43You could say no. I thought it was.

Adam:19:44It is my favorite equity portfolio.

Rodrigo:19:45I thought it was.

Adam:19:46If you’re just trying to get access to equity beta. But just we got, we wandered all over the place there. So I just want to make sure.

Mike:19:52Yeah

Adam:19:53Because Mike, you brought up a really good point that I want to, and I think it provides an opportunity for a really good example. You talked about this sort of sector universe, right, where you got a bunch of companies that are very highly correlated, they’re reacting to very similar macroeconomic factors, that sort of thing, but it could be that the, the companies in that sector are, have a wide disparity of volatility. Now, if we assume that those companies all have equal expected return and that they all have approximately similar correlations to one another, it doesn’t mean that there’s not a good optimization that may be better than equal weight.

The inverse variance portfolio that’s so, weighting to stocks by one over their variance is the minimum variance portfolio, when you assume that all of the stocks have approximately equal correlations. So that, that inverse variance portfolio is the portfolio that minimizes portfolio volatility for that, for that group of stocks in the sector. Right? So even there you have an opportunity , that may do better on a risk adjusted basis, yeah, than the equal weighted portfolio, right? So that’s just one example.

Mike:21:02But again, but what you’re saying there, what you’re saying there is that volatilities are telling you something about the portfolio, the assumption that you’ve made there is, oh wait a second. You know, the volatility thing is actually a pretty decent indicator and I actually can have, it’s probably one of the easiest items to estimate.

Adam:21:21Well, yeah, so this is a bit nuanced, right? Um, so I’m glad you mentioned that because people may mistake this. So the inverse vol weighted portfolio and now we’re really getting nuance, but the inverse vol weighted portfolio makes the assumption that all assets have the same correlation and that returns are proportional to volatility. The inverse variance portfolio makes the assumption that all correlations are, are equal, but that returns are not at all proportional to risk. So the inverse variance portfolio is a minimum variance portfolio, not a risk parity type portfolio. So it’s just a nuance difference there.

Mike:21:58You’ve mentioned the magic word risk parity. So now maybe we can jump into what is an optimal portfolio when the Sharpe ratio across asset classes would be considered equal?

Adam:22:11Yeah. So Yep. So, so jumping from the stock specific realm, right? Where we’ve sort of, I think concluded again, just to close the loop that if, if all stocks have about the same expected return, regardless of their risk, whether you measure risk by beta or volatility, then the only objective should be to minimize portfolio volatility and the optimization that minimizes portfolio volatility when you can estimate volatility and correlations, is the minimum variance optimization.

And that is the portfolio that is at the very far tip of that mean variance efficient frontier bullet, right? So just to close the loop on that, given all of the, the empirical evidence on relationships between risk and return and an equity universe, it does look like the minimum variance portfolio is mean variance optimal. And if you go and look at our papers, you’ll see that we ran a bunch of tests on industry universes, sector universes, etc. that all confirmed this with a very high level of statistical significance. So all that said, moving on to the asset allocation problem, well now you’ve got a situation where the relationship between risk and returns empirically has been very different than what we observe in the stock only universe.

As you said, across asset classes we see that returns have historically been highly proportional to volatility. So stocks have say, twice the long-term volatility of bonds and they produced about twice the long-term excess return. And so as you say, that means that they all have approximately the same expected Sharpe ratio and the objective when all assets have approximately the same Sharpe ratio should be to equalize the risk contribution across all the different asset classes. The, the method of doing that is called risk parity and there are actually a couple of different ways that you can achieve risk parity depending on what you think you can estimate.

Can you estimate correlations for example, and the type of risk that you think is rewarded in markets, are markets rewarding volatility, idiosyncratic risk, marginal risk to the market portfolio, etc. But regardless, risk parity sort of encompasses all of those different optimization methods. And the risk parity portfolio is mean variance optimal if we believe that assets have the same Sharpe ratio or they all have the same expected return relative to risk.

Rodrigo:24:50Right? So all those optimizations are trying to answer the same question in different ways. This idea of creating balance in the portfolio and max and if everybody has the same Sharpe ratio, then there are different ways of estimating uh, how you define risk and then how you estimate correlations. So we like to use them all generally in our optimizations, a handful of them, because we, we can’t say for certain than any one is going to be the best over the next five years. They’re all reasonably sound, so we want to minimize the chances of being specifically wrong.

We want to be broadly correct, we use them all. Now we have a portfolio that is balanced, that is providing the best return per unit of risk, theoretically. Does that necessarily mean that we’re going to get the best absolute return for our, for our portfolios, for our clients?

Adam:25:35Well, no. I mean, obviously there are ways that we can systematically tilt portfolios to investments that have a higher expected return. We’ve been through some of those systematic factors, uh, in, in previous episodes of this series, talking about momentum, value, trend, carry, low beta, etc. So there’s absolutely ways to, to tilt portfolios towards characteristics that are likely to predict higher future returns. The point is that if you don’t have any active views on returns, then these, these risk efficient optimizations, minimum variance optimization in the equity space, risk parity optimization, in the asset allocation space, are likely ex ante to produce mean variance optimal outcomes. So you’re going to get the highest long term expected return per unit of risk. All things equal.

Mike:26:33I love it. So it is, it is the, the, the questions we should be asking ourselves is, is what can we estimate and what risks are being rewarded. And if we can, if we can answer those questions honestly and accurately, they can lead to better optimizations. And there’s a decision tree in the Portfolio Optimization Machine paper that helps you walk through that. Now what I want to do is just, we’re running a little bit long so I do want to kind of wrap this up, but I do, we, we do want to leave you with some of the dangers of, um you know some of the out of the box solutions or some of the things that you’ll run across if you start to dig down this rabbit hole.

And uh, we don’t want you to be surprised by them or give up on some of the challenges because you know, small differences in assumptions can sometimes lead to some large swings in allocations. And maybe Adam, can you address that as, as sort of our final point as we, as we wrap, uh this session up?

Adam:27:32Absolutely. So Chopra and Ziemba in a paper in the 1990s showed that errors in returns are about 50 times more dangerous in terms of portfolio outcomes than errors in estimates of volatility and correlation. So the real danger here is in, is in misestimating returns and, and you know, even a small error in the estimate of returns can have a very substantial impact on, uh the holdings of the portfolio. And also the long-term outcome of that portfolio, I just think it’s worth giving a short example. Consider ah, a portfolio you’re trying to allocate between U.S. S&P 500, Nasdaq, and small cap stocks and Barclay’s Aggregate for bonds.

So you’ve got your estimated returns for the different stock indices and the bond index, and you’ve got estimates of correlations and volatilities. What you discover of course, is that the equity indices are highly correlated to one another. Maybe they’re expected correlation is around 90 or .95, and so when you run it through the optimizer, oftentimes what you find, even if the expected difference in returns is really small, because those markets are so highly correlated, the optimizer will just say, “well, you should own 100% of your equity exposure in one of those indices and ignore the other two completely.”

So you’ve just got an allocation to say S&P 500 and Barclays Ag. Right? But then if you, if you change your expected returns just very slightly, it will go completely the opposite way. maybe it’ll say you want ah, ah total allocation to US small caps and zero allocation S&P 500 and along with the Barclays Ag, and so this, this can cause a lot of trouble because of course as we talked about, the returns over or five or even 10 years for small caps could be very substantially higher or lower than to the Nasdaq or to the S&P, etc.

So I mean ideally you want to have a robust portfolio that contains some exposure to all three of them and it, and it’s not that hard, especially with this small portfolio to conceive of a way to do that. So imagine we know that the equity indexes are all broadly exposed to the same risk factors, the same macro economic exposures. They’re highly correlated to one another. They’re kind of like one cluster. So why don’t we form portfolios by doing this: we take the S&P and Barclays Ag, we form the mean variance optimal portfolio of those two.

Then we choose small caps and Barclays Ag, form the optimal portfolio. Then separately Nasdaq and Ag, form the optimal portfolio. Now you’ve got three optimal portfolios and then just take the average of all of those three portfolios as your final portfolio and now you’ve got a robust, mean variance optimal portfolio that accounts for the fragility of our return estimates, and that’s just an example.

Rodrigo:30:30Yeah, so the –  what this means is that if your estimate, you return estimate for the Nasdaq for example, changes then what won’t happen is you won’t then. So let’s say you’re, you’re, you’re bringing it down in the first example, your Nasdaq position will go to zero and something else will replace it. Right? And the example that Adam just described, what will happen is if your estimate changes, your return estimate changes, the weighting between the Ag Bond and the Nasdaq will change, but it will not take away. It will be part of the portfolio, it won’t be replaced by something else.

Adam:31:03Yeah, it will have a lower weight.

Rodrigo:31:06It’ll be less susceptible to drastic changes in portfolio construction. Right? So what you want to avoid when you’re doing an optimization, is you don’t want things that are highly correlated to each other that are part of the same economic risk bucket to meet in the same optimization. You want to separate those, right? So if you could go into the futures space, the same thing can be said about Kansas City wheat and Manitoba wheat. You put them in the same optimization and you’ll be in and out of those things back and forth because it’s a wheat product, there’s just a direct way, it’s the same thing.

You take them outside, you make sure that they’re never in the same, never the twain shall meet, and you will have inclusion of those asset classes without the fragility risk. Right? So that is a key thing that we need to address because of course everybody knows that mean variance optimization is an error maximizing equation. That’s what everybody quotes and that’s why it’s so difficult to use and because it’s so fragile, people avoid it. Well, there are ways to mitigate against that and you just have to make sure that you’re clustering your, your asset classes appropriately.

Mike:32:05Awesome. Well gentlemen, that was a little over, uh our normal, ah podcast time, but at the same time this is ah, a kind of complicated topic and also, uh, was one of ah, our most popular posts, so next we’re going to jump to one of our favorites. The trend, trend is your friend. We’re going to talk about trend.

Rodrigo:32:26The most hated of all factors

Mike:32:28Yeah.

Rodrigo:32:29Gotta talk about it.

Adam:32:29At the moment.

Rodrigo:32:30That’s for sure. At the moment. And we’ll, uh, we’ll see you then.

Rodrigo:32:34Thank you for listening to our 12 days of Investment Wisdom mini-series. You will find all the information we highlighted in this episode in the show notes @investresolve.com/12 days. You can also learn more about ReSolve’s approach to investing by going to our website and research blog at investresolve.com, where you will find over 200 articles that cover a wide array of important topics in the area of investing. We also encourage you to engage with the whole team on Twitter by searching the handle @investresolve and following Adam, Mike and myself. If you’re really enjoying this series, please take the time to share us with your friends through email, social media, and if you really learned something new and believe that our series would be helpful to others, we would be incredibly grateful if you could leave us a review on iTunes. Thanks again and see you next time.

Disclaimer:00:42Mike Philbrick, Adam Butler, Rodrigo Gordillo, and Jason Russell are principals at ReSolve Asset Management. Due to industry regulations they will not discuss any of ReSolve’s funds while on this podcast. All opinions expressed by the principals are solely their own opinion and do not express the opinion of ReSolve Asset Management. This podcast is for information purposes only and should not be relied upon as a basis for investment decisions. For more information visit investresolve.com

Mike:01:10Welcome back. In the first eight days we talked about an awful lot of the intricacies of portfolio construction, the assembly of strategies and thoughtful ways to increase the likelihood of positive outcomes for clients. And we dug pretty deep and now we want to think about, you know, how do you develop ah, a quantitative strategy? What is a quantitative investor, how did they develop the rules, how much should I rely on a back test, and a myriad of other questions and we want to dig into that right now.

Rodrigo:01:40Yeah, I think one of the points of this is we get, and we spent eight episodes talking about systematic investing, assuming that everybody’s on board, but there is a group of people out there that are somewhat skeptical, about a back test and the quantitative methods and the like. So, uh, you know, people had the famous saying, “you’ve never seen a back test you didn’t like”, well there’s truth to that, but there are ways to get around that as well. So today we want to talk a little bit about our journey, how we went into back testing using quantitative methods to invest in clients’ portfolios. Why we think it’s the appropriate way to do things and uh, and talk about the trials and tribulations of doing so.

Maybe Adam, you can give us a little bit of the background, some of the Tetlock research that you read early on in our partnership.

Adam:02:28Yeah. Well I think it’s important for everybody to understand that we weren’t always purely systematic thinkers. Some of us came to realize the fundamental value of systematic thinking a little sooner than others. I think Rodrigo, you kind of came to it a little earlier in your career. I had more hubris coming into the investment career than some and, and spent a long time trying to create portfolios and run the investment process using discretionary thinking, trying to figure out how the machine works through narrative construction. And it wasn’t until after the 2008 financial crisis when I think Mike and I really began to understand the power of purely systematic thinking and part of that journey was getting the frying pan to the face of 2008, but then also stumbling along or across some of the top thinkers in this space.

And one of those thinkers is a guy named Philip Tetlock, who I think more people will be familiar now with Dr. Tetlock than might have been familiar with him back in 2009 when I came across him, but just for those who are not aware of his story, back in the mid 80s, Dr. Tetlock graduated from a post-grad degree in applied psychology and went to work in Washington at some think tanks and specifically he was taking notes at political intelligence committee meetings.

So he was documenting at each of these meetings what the senior generals and senior thinkers in the military and in politics were thinking about what was going to happen. For example in the Russian politburo, who was going to rise to prominence and what policies were they likely to enact and how did it impact U.S. foreign policy. And every quarter they get together and he would read out what these experts had said in the previous quarter and what he observed was that from quarter after quarter after quarter, these top experts, we’re getting it wrong.

And they would always have excuses for why they got it wrong, and so he decided that he was going to set out on a journey to determine whether or not anybody could make reasonable accurate or well calibrated forecasts in complex fields. And um, so over a span of about 20 years, he interviewed 284 experts about their level of confidence that a certain outcome would come to pass. He solicited forecasts and a bunch of domains, economics, politics, climate, military strategy, financial economics, etc.

So he accumulated about 28,000 forecasts and he was specifically interested in measuring forecast calibration. So for example, of an expert said he was 60% confident that an outcome would come to pass, will on average over many forecasts if, if you know, they were 60% confident, then those forecasts should come to pass about 60% of the time writes that if so, that expert was well calibrated.

And so just to get right to the meat of the results after 28,000  forecast were made, he determined that experts are less well calibrated than what someone might expect from random guessing. Uh, on average, experts delivered forecasts and confidence in their forecasts that were less well calibrated, that might be expected from, from random guessing  Not one expert, there were no outliers. Not one expert distinguished himself with better than random calibration.

Rodrigo:05:55So none of them did better than, than a coin toss. Right?

Adam:05:58That’s right.

Rodrigo:05:59And wasn’t one of the stats that the experts outside of their field of expertise, we’re better at predicting the future than the ones inside their field of expertise?

Adam:06:07Absolutely.

Rodrigo:06:08Absolutely crazy results.

Adam:06:10Yeah. And, and experts that were cited most frequently in by the media or in the news also exhibited worst calibration than those experts who toiled in obscurity. So, so, so there’s good news in here, right? The good news is that alongside these expert forecasts, Dr. Tetlock also ran some really simple systematic methods. For example, uh, over the short term, the current trend will continue in the same direction. And over the very long term, we should expect there to be a reversion to the mean. And, what we realized pretty, pretty quickly was that these effects overlapped with some well known and well documented phenomenon markets.

What will, what is the phenomenon when the trend that’s in that’s currently in place continues for the, for the next little while? Well, that’s momentum or trend following, and what is a strategy that takes advantage of ah, a stock that is very far away from its long-term mean valuation? Well, it’s value investing. And so that sort of crystallized or cemented our passion in, in systematic thinking and then you’ve got Daniel Kahneman and Tversky and just a whole slew of other research that has validated that approach.

Rodrigo:07:33You go all the way down the rabbit hole, and you find yourself ready to go. Right. And this is like you mentioned, I started doing quantitative methods straight out of university because I had been lucky enough to have a father who was a math professor and a statistician. So I went into the problem headfirst. So I, I knew I wanted to do something that was rules based and what I ended up doing for the first two months of my life is something similar than what you ended up doing Adam.

And you wrote in the book that we wrote, which was grab a spreadsheet, spend two weeks, have no sleep, have 38 columns, in your spreadsheet on different types of technical indicators that are going to create a fantastic robust method of investing. Found something that had a 65% annualized rate of return and, and Sharpe of four or five, put it to work only lose like 40% in a couple of weeks. Right? So there’s a big divide between understanding that systematic investing is valuable, to actually creating something that’s useful.

Mike:08:32Let’s just pause there just for a second and just. Okay. So what, how would we define a quant manager then? Can we, can we just do that for a second? So here’s our journey to quant. How might we just sort of put a little definition into that? Adam, you want to take a poke at that?

Adam:08:48In terms of just sort of defining systematic thinking?

Mike:08:50Yeah. Well just for the, for the broad group of listeners, right? So what is a quant manager?

Adam:08:55A quant manager is somebody who realized that creating rules when you are in a calm, thoughtful, rational state that are based on fundamental intuition around economics or how agents operate in market or some other fundamental basis and then examining how that rule would have worked if put to work in markets over many, many, many samples back through time, and then once you arrive at a methodology that you have reasonable confidence in, then you just systematically execute on those rules over and over and over again relentlessly without letting emotion or intuition get in the way. Right. I mean that really that I think is, is the way that we would think about quantitative thinking or systematic thinking. Did I leave something out there?

Mike:09:44No, I think that, that’s a great, a great definition and so now that we’ve, we’ve got a common place, a common premise in which to chat about that, you can see that the world is actually full of quant managers, right? If you think about an index, the Russell 1000, that is a quantitative strategy and one of the reasons that indexes are so hard to beat or keep up with is because they relentlessly execute based on those rules and so I would, I would urge you know, listeners to understand that quantitative investing surrounds us everywhere and that you should really consider that as you’re entertaining quantitative managers and understanding how they might fit in your portfolio is that they are pretty pervasive.

And you want that, you know as, as you mentioned Adam, you want that economic intuition. You want to be thinking back to first principles on why you’re able to harness this excess return through some means so that when the going gets tough, you can keep going. Right? Because there’s, there’s a saying that-

Adam:10:51Will be tough.

Mike:10:52You know and it will. It absolutely will. And you in and under duress, you do not rise to the occasion. You sink to the level of your training, and so when the bullets are flying, and you’re in the foxhole on any quantitative strategy, you’re going to have, to have really good discipline, really good understanding so that you can stay the course.

Adam:11:13Absolutely

Rodrigo:11:14You have the rules laid out, you have the infrastructure in place so that you just keep on pressing that button, executing. We’ll that list. Even Warren Buffet is a quantum investor.

Mike:11:23Yeah.

Rodrigo11:24His quant strategy is just in a notebook and a checklist. Right?

Mike:11:27Sure.

Rodrigo:11:28And then he’s got a nice pool of money where he can relentlessly execute without getting much pressure from his, (laughing) from his stakeholders, but that, that is a point well taken. Everything’s about rules. Everything’s about making those rules based on what you’ve observed in the past. And then uh, and then systematic, the second half of  systematic, is relentless execution.

Adam:11:44The most powerful tool and probably the most widely used tool in the quant toolbox is as we, as we started out this idea of back testing or, or simulation and so, we want to spend a little bit of time talking about how we think about back testing or simulations and trying to equip investors who are not sort of neck deep in quant, day to day. Who haven’t put in those 10,000 hours but are still charged with having to evaluate, whether or not a strategy has merit to include in their portfolio.

They have some tools at their disposal to distinguish between good simulation or good quant, and not so good quant or fragile quant. But before we dig into that, I just want to make it clear that we, uh, talked about doing a podcast on that. I told Rodrigo that we’re going to get in here and our heads are going to explode because we spend all our time in this space. So I mean, really the objective here is we could go Marianas Trench deep on this thing.

We’re really just going to go snorkeling in order to just give a broad overview of, of some of the top things to think about for, that anybody can use to good effect.

Rodrigo:12:54So, so Adam, why don’t you talk about your experience, what we wrote in that, in that, in the book of your first foray into quantitative investing and use that as a springboard to understand what, what might be useful. And uh, in back testing, what, what is not useful?

Adam:13:10I think as you said, everybody starts in kind of the same place, where you get access to some data and then you dive into Excel or whatever your quantitative platform is, and you begin to create a wide variety of rules and sometimes those rules are conditional on other rules. So you can imagine ah, a rule where something is in a positive trend based on some kind of indicator and then when it’s in a positive trend and this other thing happens, then you take a trade in this direction or another direction. Oh, and then you layer on something else.

So when it’s in a positive trend and this other thing happens, and the threshold is above a certain threshold, then you take another action and imagine having 30 or 35 different layers of these types of conditionalities. What most people don’t realize is that you’re creating many, many, many multiple universes. Many, many different potential states that that system can be in.

So I go through the example in my, in our book where you’ve got 37 different indicators and let’s just simplify it and say each of those indicators has two potential states, well, if you combine all those indicators together, 37 of them with just two states each, in a conditional way, you end up with a hundred and 37 billion different potential states, for that system. And then something that people don’t realize until later on maybe in their exploration of quant is that sample size makes a really big difference.

And you need to have a meaningful number of samples for each potential state of the system. So now you’ve got 137 billion different states and you need to have a simple rule of thumb in statistics as you should have about 30 observations. So you need 137 billion times 30 total samples. So I mean it quickly. This becomes really, really, really silly, right? And so what you learn early on is that simplicity is, is absolutely the best place to start. If want to have the fewest number of moving parts, the fewest number of degrees of freedom possible so that you’ve got a large enough sample size to make meaningful conclusions.

Rodrigo:15:21Yeah. One of the examples is that I like to give is that first model that I built out, was right 92% of the time, so it had a huge edge. 92% of the time I’m going to be right, but it only happened five times, right? We only observed those 35 parameters hit five times in history, so small sample size, huge edge. In sample that is ah, four Sharpe strategy and then you have these more traditional momentum-trend-value strategies that have thousands of observations but a small edge, 51% of the time, 52% of the time.

And once you go live you find that that one that I created just loses money and the other one is wrong. 50% of the time, roughly actually 49% of the time. But having it that at 51% edge over long periods of time is massive. So it’s just a tough pill to swallow that you’re not going to make all this money in a short period of time. It is a small edge, and a series of small edges pay up over time. That is that it really ends up being as, as, or at least as, as simple as we can make it for now.

Mike:16:28There’s been lots of literature written on, on the point of humans trying to follow algorithms too, and the behavioral challenges that they have with that. And so Rodrigo went through the process of finding something that was right 92% of the time so he could have comfort in doing that. Even if you have that strategy and it goes wrong once, humans have a really hard time following it, even if it was right 9/10. And now you can imagine here, you, you, you know, we’re going to talk a little bit more about ensemble methods and the fact that you know, lower, you know lower probability of success but across many systems is more effective.

But here you have a system that might be 50% or 60% effective and you know, size of win also, um affects that as well as not just the percentage that you’re, that you’re right.

Adam:17:15For sure.

Rodrigo:17:17But so, so now you can imagine you’ve got this system that’s right a little bit more than a coin flip, behaviorally that’s really difficult for, for a human to stick with. And the research on this is, is incredible, right? If, if an algorithm is wrong once, it’s dead to people.

Adam:17:32Well it’s, it’s even simpler than that, right? Some of the psychological literature you’ve got experiments conducted over and over and over again, where you, where you give somebody a loaded die, they know it’s a loaded die, they know that the odds are massively stacked in their favor. You get them to, to throw the die over and over again. Well, if they throw the dye, and they get a losing outcome, they’re less likely to bet the next time. If they get a second losing outcome, they’re even less likely to bet, and they scale back the size of their bet.

So, I mean this is even knowing, what this is in markets, can’t know anything, with a loaded die, you know, over time you’re going to have, you’re going to have winning outcomes. So I mean this is just a ubiquitous facet of human nature that is inescapable, and we need to be aware of.

Mike:18:13And especially when we’re building algorithms and systems like, you know this is this, this is a human frailty that you want to make sure that you’re, you’re aware of, and even though you’re aware of it, you’re still susceptible to it, but you’re, you’re, you’re not letting that impact the build out of your quantitative strategy.

Rodrigo:18:32Yeah. When you’re a quantitative firm, I mean you do enough work that you recognize that it’s all about relentless execution. There’s a ton of simple systematic methodologies out there that are being used by individual investors and individual advisors for their clients. And if you’re new to it, I don’t think most people realize how difficult it is to pull the trigger. Right? For us, it’s second nature. We don’t even pull this trigger anymore. We have a whole operations team that pulls the trigger.

Mike:18:55Oh my God, you’re so right. Remember what year was it in January, was it 16, 2016. January, February. We heard about all of the other sort of 10 month moving average strategies being entirely in cash and they’re intense discomfort with that. And I’m.

Rodrigo:19:16Oh yeah, January, 2016.

Mike:19:17Yeah.

Rodrigo:19:18A bunch of these uh, managers went 100% cash and we talked to them and they’re like, we’re terrified. We’re terrified what’s going to happen here? But I even have a very close to home example. We, when I first got into the business, I worked with an awesome, awesome human being who built his book of business talking about the, uh, what was it that he used, to used the 10 week and 40 week moving average crossover.

He called it the golden cross or whatever. And that’s how, that’s how we, he did everything right? And he used a Nortel example when it crossed over, you would have been out at this price and you would have been back in at this other price. So he goes years and years talking about this. But the reality was that we hadn’t seen a cross over for a few years, a bunch of years, and all of a sudden in September, August, September of ’08 you see the Toronto Stock Exchange crossover a bunch of the stocks that he was wanting to crossover.

I wasn’t working with him at the time. I reached out, and I’m saying, “You’re getting, you’re getting out, right? You’re selling out.” And he said, “You know I’m gonna, I’m gonna, watch it for a bit. I’m not sure this is a confirming signal.” And he never got out and it just, it was that difficult. Right? You can spend your whole career talking about what you’re going to do, but it’s another thing to actually execute on it.

So if you’re going to get into quantitative investing, even if it’s simple models, especially if it’s models that only trigger once in a while, make sure you are ready to pull that trigger when you need to.

Mike:20:36So let’s, let’s jump into how we might improve on. Given the concepts we’ve laid out, how might we improve the opportunity to gain a signal? Let’s dig into the ensemble methods a little bit more. What you guys think?

Adam:20:49Yeah, sure.

Mike:20:50It’s a good, good jumping off point on that.

Rodrigo:20:51That, that, that will also be another hour that will eventually do, but I will. Let’s see if we can get it done. Yeah. Yeah. Let’s talk about it briefly. It kinda, it parlays from the conversation of the 51%. And Adam, I know you’ve done a lot of work on this. Can you give us a brief outline?

Adam:21:07Well, I think the best place to start is, uh, we’ve talked a little bit about this in previous episodes, but it’s worth revisiting Larry Swedroe’s framework for evaluating the most constructive or prospective edges, right? So something that’s pervasive works across different markets, persistent works across different timeframes that it has economic intuitions, so when the chips are down or when your strategy hasn’t been performing well for a while, you have a reason to maintain faith in it, that it’s implementable in practice, uh, survive transaction costs and liquidity and market impact and all that kind of stuff.

And so the question is how do you account for those variables in the back testing process? And it comes down to stuff like, so you’ve got an investment universe that you’re going to use for testing. How about you mix up that investment universe? So you’re going to use REITs, let’s do use different, different REIT indexes. You’re going to use U.S. equities, you are going to use different U.S. equity indexes, you are going to substitute the Nasdaq or the Dow for the S&P 500  or U.S. total stock market.

You’re going to use different tenures of bond indexes. You can use foreign and domestic bond markets. You’re going to use different types of commodity indices, these sorts of things, right? Because you want to make sure that your process is robust to a variety of different specifications. It could be just that you discover a process that is uniquely engineered to the idiosyncratic qualities of how a certain market evolved in the past, and that that is, um, that that will not translate into the future. And so you want to avoid creating strategies that have that level of fragility or, or sensitivity.

Mike:22:44And across how many domains are you doing this? Right? So what timeframes might you be looking at? What metrics might you be looking at?

Adam:22:52Absolutely, or different ways to specify your indicators, right? So you’re going to use momentum, is it six month momentum, is it twelve month momentum? Are you going to…

Rodrigo:23:00Lets define what that means? Right. Let’s think about momentum. So what is it momentum trying to do just as an example? Well, it’s herding behavior. We think that there is a real behavioral reason why people tend to do things that are, go into things that have recently done well and get out of things that recently done poorly. Okay.

Adam:23:18Sure.

Rodrigo:23:19The academic approach to that is to look back, rank asset classes and securities over the last 12 months and then pick the top…

Adam:23:25Skip a month….

Rodrigo:23:26Skip a month and then and then hold it and then rinse and repeat over and over again. Okay. That’s one way that’s herding. One way. Why is that the herding behavior parameter? If we use 20 days does that seem to work? What about a six and a half months or anywhere between …

Mike:23:39137 days?

Rodrigo:23:45Right? So they all seem to survive. And they all seem to have over very long periods, is similar Sharpe ratio.

Mike:23:51So, so let’s dig into this a little bit so, so that someone out there can maybe use this a little bit more in a real example like momentum. So we’re going to look back and we’re going to say we want to, we want to think about momentum in this ensemble framework, and so someone might be able to more concretely grasp what we’re talking about. So I remember growing up in, in this world of finance and reading O’Shaughnessy’s book back in the mid 90s, and he had the Compusat database and I’m pretty sure it was nine month momentum that nine month was the, was the sweet spot and then, and then it became the six month momentum which is the sweet spot and, and I see this pervasive across lots of tests everyone’s using the six month and, why are they using the six month? Why was the nine month to use?

Well, because after the fact it was the best one and so, but that, that doesn’t mean it’s going to persist into the future and we don’t know. We know generally speaking, that momentum exists anywhere from, I don’t know 20 days to 300 days, but it’s going to move around in that area and so you have the opportunity to make some pretty big mistakes if you’re just saying, “I’m going to use six months.” And so maybe you say, “Well, I got you Mike. I know what I’m going to do. I’m going to use three month, six month, nine month and twelve month.”

And it’s like, “Okay,” Well we’ve seen pricing behavior. What about when that one month, that moment when you’re looking back and observing your back test, happens to be 3% to 5% different than the actual meat of the trend, right? What happens when that one observation.

Rodrigo:25:26What happens is all the information in between?

Mike:25:29Right.

Rodrigo:25:30Yeah.

Mike:25:31It’s an outlier. So, so you’re missing all of that, that’s okay. So now I hope people are starting to sense. Oh yeah. Well what about when that happens? Okay, well let, let’s, let’s dig into that a little bit deeper. What kind of momentum are we talking about here? We’re talking about point to point, price momentum. So let’s say something has a zero price for six months and then on one day it gaps up 6%, making it the number one performing asset in your universe. Is that reflective of the returns that have been garnered for clients over that timeframe? Is it reflective of the future?

So maybe one of you guys can jump in and, and talk about how we deal with that and the different types of momentums we might use. Because …

Rodrigo:26:08I mean you just talked about one aspect of the momentum methodology, which is how far back do we go to rank asset class momentum or strategy, security selection momentum? Why aren’t we assuming that momentum is best extracted by looking at the price percentage outcome? Why don’t we rank it based on Sharpe ratios or rank them based on the days they’ve been above a certain trend or so on and so forth, but we have a piece called The Many Faces of Momentum that people can read in the show notes that walks through the many ways of trying to extract…

Again, going back to the fundamental reason why we care about it, humans are going to likely continue to herd. That’s what we want to do. We went, there’s this momentum signal going out into the atmosphere. We want to be able to hug it and as many ways as possible, in contrast to trying to build the best antenna. If there’s a signal you don’t want to build the 6.5 month antenna that recently captured the best performance, and you can show that I have a bigger edge and momentum and somebody else. No, you want a hug it. You want to, you want to do a lot of small edges, a lot of simple antennas that together as ensembles are able to eliminate the error terms and capture the true signal, right? Maximize the signal and minimizing noise. And that’s what we mean by ensemble method.

Adam:27:20I just think it’s important more generally just backing it up a little bit for people to realize that the history that we’ve observed is just one potential trajectory and you shouldn’t get too caught up in the precision of the rules that you’re able to derive from that one historical context. I mean, the idea here is to be generally correct and to avoid the potential for being specifically wrong. I mean we’re trying to connect with. We believe that a certain phenomenon exists. We have a great deal of humility about the way that it exists or the way that we would measure it.

We think there’s a variety of valid ways to measure it, and it’s just more reasonable and more humble, a more humble approach to take all of these different methods to measure it and then aggregate them all together. Um, and you know, as a starting point, just an equal weight. And then, I mean maybe at some point in the future we can talk about, ways to use machine learning to maybe skew towards certain specifications and away from others, that sort of thing. But really it comes down to humility. Trying to catch a phenomenon with a net rather than trying to hit it a square with a sniper rifle.

Rodrigo:28:32Exactly. I think that’s kind of what we wanted to get out of this episode today.

Speaker 2:28:36Yeah.

Rodrigo:28:36Really helped people understand good back testing, bad back testing, ensemble methods, making sure that we’re attacking the problem from humility and not finding the best possible max Sharpe back test that’s gonna kill it and it’s all just, um, uh, you know, reverse engineering.

Mike:28:54Generally correct. Not specifically wrong, right? Uh, what we’re trying to avoid luck, both the good luck and bad luck. I mean, another great example is just days of the month in which you would be balanced monthly systems, monthly systems can have variance in the Sharpe ratio, 50% based on what day of the month you happen to rebalance them.

Rodrigo:29:11Yeah. And we, we covered that in a piece recently called “Same, Same but Different” that I encourage everybody to read.

Mike:29:19Lovely. All right. I hope that helped. As always, if you do have questions on an episode like that where we got into, uh, into things a little bit more deeply and you want to know more, you can always reach out to us. We love that. We love having conversations on this topic as you can, you can tell, and that wraps up.

Adam29:37Thanks guys.

Rodrigo:29:39Thank you for listening to our 12 days of Investment Wisdom mini-series. You will find all the information we highlighted in this episode in the show notes @investresolve.com/12 days. You can also learn more about ReSolve’s approach to investing by going to our website and research blog at investresolve.com, where you will find over 200 articles that cover a wide array of important topics in the area of investing. We also encourage you to engage with the whole team on Twitter by searching the handle @investresolve and following Adam, Mike and myself. If you’re really enjoying this series, please take the time to share us with your friends through email, social media, and if you really learned something new and believe that our series would be helpful to others, we would be incredibly grateful if you could leave us a review on iTunes. Thanks again and see you next time.