SI419: What Happens When AI Starts Building the Portfolio ft. Nick Baltas

(upbeat music) Welcome to Top Traders Unplugged. In markets, success doesn't come from predicting what happens next. It comes from being prepared for what you can't predict. In each episode, we go deep with some of the world's most thoughtful minds in investing, economics, and beyond to understand how they think, how they prepare, and how they decide, and the experiences that shaped how they see the world. No noise, no shortcuts, just real conversations to help you think better and invest with confidence. (upbeat music) (upbeat music) Welcome back to Top Traders Unplugged where each week, we take the pulse of the markets from the perspective of a real-space investor. My name is Alan Don, and this week, I'm sitting in for Niels, who's away on his travels, and I'm delighted to be joined by Nick Palters. Nick, how are you doing? - I'm doing well, Alan. I'm doing well, how are you? - Good, I know you've been traveling as well, so there was a bit of tension earlier, where you're going to make it or not, but you're here in good shape. - But I'm here, I'm here. It's been quite a quite a September, obviously, back to school, back to back to work. It's been very, very busy, and the kids going back to school, and my son starts nursery and all that a lot. So it's been a busy month, I must say, but all very good, all very good. - Good, yeah, well, it's busy, and a positive one for trend following sets that always helps as well. So everybody in the industry, I'm sure, is in good spirits, but we do always like to kick off with asking our guests, what has been on the radar? What's been on your radar in the last several weeks? - So, I don't know if that's something in my radar, but certainly something that you know, that just got my attention, and I don't think it got just my attention. I think it got various people's attention, and it was part of a small article on the FT, a couple of days ago. This comes from GS, from Christian in Lug Lisman, he's running our kind of multi-acid strategy on the research side, and he put out a chart, which is like, this is very, very simple, but actually quite striking. So what it shows is that, sorry, it shows basically the percentage of S&P 500 constituents, so 500 socks in the index, that have a negative beta to the index that they belong. So naturally you think, if I belong to an index, then more likely I have a positive beta to it, partly because I'm part of the index, obviously at smaller sizes, you would expect that this will become less direct, but also because there's a significant beta factor that is driving assets and stocks in this particular case. So, using like a three-month calculation, point in time, it's 45%. So about half of the stocks in S&P 500 have a negative beta to the index, which I think is just mind-blowing. Last time that we had this situation was in.com, but at the time, the number was just a tad less than 20%. It's now almost 45%. And obviously, the background here is the fact that S&P is a cap-weighted index. The AI dominance is effectively building its own kind of mini-index within the index, and all the rest are becoming less correlated to it. So this clustering and concentration is basically causing this effect, but again, that in itself is quite a striking image, once you see it. I know you've seen the picture, so. - I've seen the picture. - You can relate, right? - Yes, there you are. - You can relate, there you are. I mean, it shows the dramatic, well, it looks like an acceleration on the chart. I mean, people can check it out. It was in NDFT, so you'll see it online, or check out Goldman's research. I mean, is energy probably is driving it to an extent as well, I guess, is that so? - It could be good. I mean, there is not too much discussion in the actual paper from creation on that part, aside from the fact that the market is getting concentrated, and there's a lot of discussion as to whether bonds are defensive in this current environment, and obviously this decoupling in the equity space is creating opportunities for dispersions, and people talk about, you know, going long correlation and so on and so forth. So that's kind of the background under which this was kind of projected, but that in itself, even out of context, is quite a chart. So, not necessarily in my rate there, but let's say some that caught my attention in the last couple of days. - So, no, no, no, no, it's worthy for sure, yes. - Well, on my radar, I mean, probably similar, in the sense of more noteworthy, I would say, is I've just been following the debate in markets and amongst analysts about rising yields. Obviously, everybody's been talking about the bond market, the bond markets around the world for the last number of weeks, but it just really strikes me quite heated debate in times between analysts as to what's driving this rise in yields as to whether it's, you know, is it economic growth? Is it fiscal concerns? Is it that people expect rates to be higher on average over time? Is it the competition for capital? And has that been driven more by budget deficits? Or the AI spend? Is it the debatement credibility issue? So, all of these things, and everybody has their own view. I mean, it is striking from my perspective. I mean, I do think the fiscal story is there in the background, but at the same time, if what's really struck me in the last couple days, just looking at it is the big repricing at the short end. I'd like the two-year yield has gone up, I know, 75-bips are maybe a percent, at least 75-bips, I would say, since the middle of August. So, does it mean this? And also, at the short end, around the world has repriced. So, it's as if everybody now has taken a much more bullish view on global growth, or I'll see, you know, the conflict in Iran and staying on much longer. But I suppose my perspective on this is this kind of tendency amongst analysts to view the fundamentals, and then the market reaction has been very much linear and proportionous, as opposed to, you know, markets are complex adaptive systems. It's given change in the fundamentals at one time, kind of a big impact, other times, kind of a small impact, marketing position matters, as we all know. And the market dynamics do people have. Barriers being hit, hedges, et cetera. All of that seems to get removed, and people are trying to find this very linear cause-and-effect relationship, which I don't think exists. But I'm curious to hear what's your perspective on yields? Do you lie in bed at night wondering why yields are rising, or did you just take it as face value that they are trending higher? - I mean, I'm looking into my, you know, my mortgage is at the minimum, and I'm trying to project what's gonna happen the next time we have to do the mortgage, but I guess jokes aside, I mean, some of them was having quite substantial. To your point, we've seen some kind of multi-year, or perhaps the K records in the US, in the U.K. as well. And even six months back, is it six months? Maybe six months back. Analysts were projecting rate cuts. Like for those that have forgotten that this was the case, that was back in February. So it's not that long ago that the projection was, that we're entering into kind of these normalization states whereby central banks will start kind of easing, and all we're seeing now is actually yields in reaching those kind of levels that we haven't seen for some time. I don't have a strong view, frankly speaking, and I wouldn't claim any particular expertise in that space, the one thing I would say, and that was like a quote I heard recently, and I cannot recall exactly where this came from, but it was more about, it is very hard to predict, not only so, because prediction is hard, but sometimes you cannot even tell that today's situation. Like to your point, it is a struggle to understand point in time. But what is actually happening in the market is that a lot of predicting are markets. Obviously that was not a quote, that coins would be extremely happy about prediction and so on and so forth, but I think it's painting the picture of how complex markets are today, whether we see geopolitical tensions kind of running ahead of us, whether that would have inflation implications, whether the inflation is more of a reaction to it or the cause of it. At the minimum, I think rates have been the strongest contributor to trend following strategies. Absolutely, I would imagine most programs would be short and benefiting quite substantially, months to date and a year to date. Yeah, well that's a good segue. We do always like to give our performance updates, and as you say, it's a good month for trend following the soft trend up about 3.7% on soft trend CTA index, up about 3.7% as well. And year to date, both soft trend and soft trend CTA up about 15.2%, 15.25% to pretty much neck and neck. And as we were chatting about just before we started recording, that monthly number probably understates a little bit because it's up to the 20th and yesterday was also a pretty good day. So, very good month, very good year. And as you say, certainly this month looking at certainly across the managers that we allocate to, very much by say, an 80% of the cases concentrated in fixed income, short positions, and at the long end as well. Obviously, as I mentioned, there has been a very big reprise and so, you know, interested features, two-year yields have had a big move as well as the more publicized move in bond markets. And I think this is often like really the, you know, where people see huge value in trend following as an element in portfolio, because if you think about it, if you've got a 60, 40 portfolio and you've taken it, some of the allocation and added it's trend following, that trend following exposure now is short bonds. So that bond short is basically taking down that your core long position in bonds that you would have had. And by adding trend to your portfolio, it probably be net short bonds in this move up. So that's the kind of environment where you really see the value of it as well as also, in August, we had more long positions in commodities that we're contributing, but certainly this is the kind of where you're seeing that kind of dynamic element of trend following exposure, whether it can do to a multi-ass portfolio, which I think is very valuable. And it's been a good month for you guys as well. I think you were saying performance wise. I mean, it's been a very good month. As you say, I think it's one of the stronger months that we've seen in a number of years probably. I think, I think, January was very strong this year. And obviously, the month that we went past August, I mean, the rates significantly outsizing contribution from anything else, commodities and equities, obviously come second and third. But you know, at some margin, which is basically driven by this month's activity. So the fact that, you know, said differently, beginning of the month, rates commode and equities are basically kind of equal contributors to performance. And now that that gap has widened by some amount precisely because rates have doubled their contribution. So it's been it's been it's been essential. Carst is a bit more of a mixed bag. I would say you're afraid nothing very extreme on, you know, in the direction, I think with a with a dollar moves we've seen. There's a bit of a lack of of trendiness, which was against, by the way, for rates, until maybe what Q2, we haven't seen actually rates kind of trending. It's been more of a last couple of couple of months activity. But it's against that's the other benefit of the diversification, different, different contributors in the rest of class at different points in time. But that's a very good month and a very good year so far. I think it's a third best, at least from some of the stats I have. I think it's a third best so far here in the last 15. Okay. So 2014, obviously with a dollar and the dollar moves. Yeah. 2022. 2022 and then this year. Yeah. So far so good. So far, so good. There's always there. There's always the last day of the month or the last day of the year to navigate. But as you say, it's been a good month. It has been very good. And I think you make the point as well. I mean, yields had been in a range. Like if you look at the 10 year yield, it had been a three and a half to five percent range since, you know, October 2022. Yeah, you know, well, we've touched, yeah, we've sawing it had been very difficult. Obviously the market had priced in a recession probably three times since 2022. And now has flipped back towards a much more positive economic growth scenario. And now we're certain to see that move accelerate. So interesting to see how that evolves. It's interesting to me. I just looked at a few days ago. So I'm not sure if it's moved much with the more recent run up. But volatility in the bond market has been relatively contained. It's been a very stable. I mean, the magnitude of move has been sizeable. And obviously, I think when you breach a psychological level, like five percent, people tend to get very excited. But at the same time, from a volatility perspective, we're not seeing rising volume in the bond market. No, no, no. I mean, and I'm seeing that also in the strength of the signals, which are typically volatility scaled. And I know they haven't basically shrunk. Or let's say they haven't actually moved, sorry, they haven't stayed flat. You could argue that, you know, the yield move you see if it comes at higher vol, the net effect, volatility is like flat. We haven't seen that the case. And what we're seeing is like a strengthening of those of those signals, which attests to the point that the move has been greater than the volatility at which it comes along. Yes, yeah. And as people maintain those positions, the penal attribution is that much greater than if you were seen a very choppy and volatile run up. So that's favorable too. So let's see, equities. Equities is a bit more challenging for the month, right? Because you know, you came into the month long and then obviously, most of the markets have kind of attracted not by a significant amount, but that's, you know, that's not like a positive month for equities, not too negative either. Yeah, like less than a percentage, for example, I'm seeing some stats now. And commodity has been a standard in August. Mixed back for the month. So you know, you have some obviously some of the energy markets kind of performing, but then some of the more acts and softs have not actually delivered any performance, or maybe detracts some performance. So like flat, flat for the month. It's actually quite striking that they must like not flat, flat, flat, except for it's. Yes. I should say. Yeah, yeah. Well, that's pretty much that's the story, by the way. That's the only story for this story. It's a great story. It's a great story. Yeah, that's about it. 2022, I guess, was a great story, but it was also a dollar story as well. Yeah. So that accentuated. It was a bit of commodity story, like in Q1 as well. Yeah. The inflation moves and obviously the geopolitical tensions as well. I want to move on to some of the topics that we had prepared. And I suppose on the theme of that mix of volatility and trend and how to condition trend with volatility. And there's a paper research that I note that came from the guys at Alpha Architect recently around the whole area of whether you can enhance the trend system or a momentum model by looking at the volatility environment. So basically, you know, the idea of trading faster in higher vol markets or trading slower in lower vol markets. You had a chance to go to the paper. Yeah. Yeah. I mean, I did take a look and I kind of thanks for pointing it out. I mean, the results are actually quite straightforward. And the methodology I have some kind of question marks around it. But as you say, the, you know, the punch line is should you adjust your kind of look back window as a function of all, you know, if all increases, should you go faster? If it drops, should you go slower, kind of reduce some of the false positives? Does that bring any value? That's kind of the high level question. Yeah. But then if you like the approach, it's actually very simple. And there could be nuances that relate to the results that come from the design choices. Yes. And it's unclear to me whether we can generalize, but to kind of go a bit step by step, they're looking into, and by the way, the whole idea is that this was a research paper done in September 2017. So they wanted to now extend with nine new years, if you like, in the, in the sample. And see whether this kind of VIX dependent, they use it mix as a measure of all VIX dependent look back windows, bring more value vis-a-vis static window. Yes. So it's this extension of this kind of research, 90 years later. So the whole idea is about allocating into nine, sorry, into five ETFs. So they have, and I'm kind of checking the least, S&P, U.S. equities outside of S&P, international equities, global IG bonds, and then short term U.S. Treasuries, those five ETFs. And the way that they designed this, let's call it trend following strategy, is that they choose either based on a dynamic window or on a fixed window, either the best or the two best assets out of the five based on their momentum. Now, a few details here, this is to a certain extent more of a cross sectional momentum strategy, because if you're picking the best, it is not clear that this is a long or a short position, but it just happens to be the better of five. And obviously the same applies for the two. There is no shorting, so it's a long, only portfolio. You're always long, the outperformer of the five or the two outperformers of the five. So we can just throw the parallels or maybe the differences to how trend followers would look at it. From a directionality, not just the relative performance perspective, that's point number one. Point number two, the fixed window uses 10 months. I don't know what is the 10 months. I don't really personally use it, but I guess it's 200 days. That's the closest I can get to. It's like a 200 kind of moving average or some sort of a 200 days of a signal. That's the fixed. And then they have kind of three windows depending on the level of VIX. So if VIX is too high, they go very short term. I can not recall exactly the numbers, but let's say short term. If VIX is in an intermediate range, they go to an intermediate window, and then if VIX is low, they go to a longer window. Now obviously, as soon as you use VIX triggers, everything becomes very parametrized, and quite sensitive to the choices you're making. As an example, the periods of high VIX in those nine years of extension of the research are are just three periods, three months, actually. But the way they do mastery balancing, which is another perhaps more of a simplified assumption. I mean, in all fairness, and I guess being fair to the approach here, possibly it's the audiences a bit more retail oriented. So they're looking at let's say five ETFs, how can I allocate between the five ETFs? Should I use kind of momentum signals and fix? So we know with three data points in what they call the red zone, I don't know how much statistical confidence we can build. Which by the way, it's fully disclaimed in the article. And then the last point that I would flag in this whole kind of design is that either you choose the top out of the five or you choose the first two out of the five, and if you happen to choose the two, you would allocate $50-50 national. So there's no volatility scaling, there's nothing as such. So very, very simple design. Top one or top two equal weights in national terms, monthly rebalancing. So there is no follow the trend, no risk scaling, no optimizations, no risk allocations, there's none of that. - So you say it's pretty much aimed at an RIA type audience managing perhaps long-only portfolios and then assessing the merits of adding a momentum overlay. - Perhaps, but there are times, for example, that you might find one variation out performing the other because one is in S&P, the other one in Treasury, but $100 in S&P is not as much more risky than $100 in Treasury, right? But that is the mindset here. We were talking about a fixed national. So it's a fixed national allocation. So with all those caveats in place, what they find broadly speaking is no significant value above and beyond a 10-month static look back. There is an argument that when you choose the best out of the five, you're kind of outperforming, but frankly speaking, it's a period between 2020 and 2021. And that you happen to be a bit more kind of moderate, that volatility wasn't too high, but it wasn't too low at the same time. But if you look into the details, the rest of the periods, there is no statistical outperformance and either outperformance. Obviously the good questions what happens after cost and they have some analysis on this one. When they use the top two, there is no significant difference at all versus using the same two, but coming from a fixed window. So all that to say that there is no contradictory information to what I guess was the case back in 2017, perhaps there's an argument that I know without statistical confidence, there is some value. But as we know with these type of studies and those triggers, it is hard to make a statistical case and triggers themselves by nature, lend themselves to very low statistical power because you need the trigger to be activated and guess what? The trigger is not going to be activated at many times because if it's too many times, then it's not even a trigger. So the whole trigger, I'm not personally like a big fan of triggers in a strategy. It doesn't seem in that case to add significant value. That's the whole story, right? But. - I mean, selecting one condition on the VIX, I think did I perform, but I should say it was very much linked to, I think it was November 2020. - Don't do that exactly. - Which was the month when the COVID vaccine was announced. So the small cap stocks, I think they were updating percent I checked. - I think it was like. - Of 10 or 11, yeah. So. - I think I was looking into this one just a second ago. I think SNP at the time was like exactly to your point, like in a double digit, and then the more kind of static strategy had like in the treasuries at one percent. - Okay. - Yeah, yeah. - I mean, I just thought it was great, right? - It's a concentration and small number of instances driving some of the changes. But I mean, there is, I mean, it is certainly a, I suppose an idea that I know some managers do model and do integrate into their train strategies. This idea of trading faster when market follows higher and slower when it's not, sure, when the slower is, have you looked at it yourself? - So, I mean, that's the point I wanted to make as I guess as the next remark, above and beyond what this article discusses. Volatility for us is a very important indicator and it's utilized in other places. So the way that we approach portfolio design is not dissimilar in that mindset to utilizing volatility to be more dynamic. But instead of us utilizing a different kind of window depending on volatility, who we scale our signals by volatility. So we're looking to signal strength that by nature, more volatility regimes would bring your strength down. And if that is the case, depending as to how you do volatility targeting at the top level, it could have implications as to how much risk is eventually deployed. When those moves happen, I guess in a coordinated fashion, not only do you have volatility spikes, but you have correlation spiking, which also has implications on how much dollar and rational is required for a specific volatility target. So I'm not in this agreement of utilizing volatility, it's just that the way or the lengths through which I utilize personal volatility in, I guess, or in our research philosophy, comes through the portfolio design, comes through the scaling of the signal, comes through the risk budgeting between the assets. So it's a bit more convoluted discussion. Without necessarily having to use a trigger, rather a continuous function, because your scaling by somebody's continuous, your estimate of all, to scale your portfolio and to assess the relative strength of the trends signals. Obviously we're not using peaks because every asset will have a different volatility, but in the context of utilizing market volatility, we use parts thereof and the correlation structure as well. So that's how we'd look at it. - Yeah. - I mean, essentially, it's kind of a regime classification. - Yes, yes, yeah. - So if I come to that point, then the whole discussion becomes, can we identify a regime whereby a correction is more prevalent and is going to be more extreme? And if we could, then we could time-trend following. So now we're pivoting into the camp that says, maybe we can identify trend regimes and maybe in that context, we can utilize the volatility of the market. I mean, the reality is that this is a very, very hard gig and I wouldn't necessarily argue that I can prove statistically, at least using data, that this is a worth pursuing if I may say. - I think these are all areas for people to look at and from the perspective of trying to hand, I mean, obviously, mention it using volatility as an import in terms of market sizing and scaling. But then I suppose it's then taking Val as another import as either a regime classification indicator or saying something about the likelihood of maybe an equity correction. - I think, I think my principles and it's something I've discussed here, maybe with you, maybe with Nilsis that there are periods that we can accept the fact that predicting a reversion is hard or that there are no real trends in the market. And you know, as you said earlier on, we've been in the right space now in the last few years with no specific direction whatsoever. So perhaps the prudent thing to do is to say, well, look, I just succumb to the temptation of identifying any trend on something that is looking almost like in a white noise. And I make either an active call to get out of some of those markets because I'm lacking conviction or I'm looking for systematic profiles that benefit from those regimes that would be complementary to trend following. So rather than trying to make the model much more parametrized just to make it work, I think to me, it's fair to argue that, hey, this is supposed to be doing what it's supposed to be doing when trends exist, if they do not exist, I'm not gonna try to recreate them with a more complicated structure other than find other components that would allow me to navigate through and perhaps complementing my trend allocation is the prudent thing to do for like long-term viability of the allocation. I mean, that's my mantra if you like in this regard from a perspective. - It probably is fair to say though that, I mean, if you look at the performance, the short-term managers and short-term momentum, did you trend to be, tend to be stronger when you get higher, probably higher realized while I tell you. - For sure, for sure, for sure. - But I guess my point is that is that a feature somebody should introduce to a more dynamic model because I would not disagree that being faster will get you better around turning points. But my question then is, do you time the turning point or do you happen to be fast and when this arises, you happen to benefit because you're there. So, it's my point, right? Calling the reversion is very hard. But if I were to be utilizing a fast model, I would have gotten it on time. The question is, can I deploy that speed dynamically? And will it be fast enough to cut my exposure? I think that's a big question. No, I hear you. Yeah, yeah. That's a big question. OK, fair enough, interesting. Sounds like you're not going to be making any media changes on the back of these ideas. You're pretty stable in your assessment. I think I have some views that that is a fair point. I mean, making changes using triggers, specifically in that world of QIS, is not an easy path because proving statistical value is impossible. Just because you don't have that many observations. Like, no, when this particular article talks about three months. Yes. That you know. I know. I mean, I was in a conversation recently. Somebody was like, no, discussing about a specific indicator or achieving two-to-time specific market events. And I was like, OK, that's great. Tell me your false positives. And then we're going to have a conversation. Because great if you can pick the turning points. But if you pick another 30 turning points out of 33 in total. Then I'm not sure sure that those three that you picked right are actually valid. But you know, jokes aside, I think the way that the markets have been operating recently in the last couple of years. And we've discussed that quite a length with very short-lived false spikes that moderate very, very quickly. These are all the V shapes that we have seen basically one per year for the last four years. I think these can cause significant disappointment if somebody were to follow an unconstrained trend follower. So in some respect, I think they do create an invitation for some thought to be put into how we act and interact with those V-shaped markets that we know. We start seeing more often. I don't know if that is related to the economic regime or to the kind of current presidential status in global markets. But the reality is that we have seen them. We have seen trend following going through those V shapes with a bit of a scar. Thankfully, we're now here a year and a bit since the last V shape or at least the last more aggressive V shape. I think the March event for this year was not as contagious as liberation day was with trend following having done really, really well. And I think keeps on kind of getting attention from museum investors. Very good. Well, switching gears. It's a second paper that a paper that you highlighted. It's very interesting and very topical. And it's in the whole area of applying an agentech AI to an asset allocation portfolio construction process. And I mean, it's certainly reading at a high level. It's very much an eye opener as the way things may go looking forward in terms of institutional asset allocation. But the paper is from Andrew. Do you want to give us, I suppose, the overview of the paper and then can enter your thoughts on it? Yes, yes. I mean, obviously, as I said, we're shifting gears in a way. But I don't think we're shifting gears too much from how institutions kind of manage their assets and how asset allocation is perhaps getting reshaped in the world of agentech AI. So this is from Andrew Wang. I would imagine quite well known. He used to be an academic at Columbia. Then he used to be kind of the head of factor investing at BlackRock. And now he set up all bridge with another two of, I guess, of his co-founder. So that's basically one of the first papers I would imagine. He basically talks about agentech architecture for asset management. And I mean, those that haven't actually seen it and have read, like, no, the last few days with a bit more detail. It's actually quite fascinating. Or a person we kind of found myself kind of drawn into it. Just because you start seeing how the, you know, the transition into agentech AI could have implications in many things that, you know, historically, we used to do using people and processes and time and various parts of that process could be now abstracted. Obviously, human in the loop is extremely important. But then that human in the loop becomes more of a supervisor, more of a, and the fiduciary, deploying, if you like, those recommendations, and having, if you like, a sense of the, you know, of the truth versus the false positives in that respect. So how the whole story plays out, and I'll try to summarize the paper if I manage. It's more of a nice story kind of to go through because above and beyond, it's almost like a framework. Let me just start by saying, what is the overall process? The overall process is that, let's assume like, you know, you have like a big institution. A big institution that, you know, has to put together a dynamic portfolio of multi-plus classes, given a certain level of risk or maybe appetite or kind of guidelines. And it all starts with, I guess, a policy statement. You know, what are the risks? What are the risks we can run at? What is the volatility? What is the expected return? What are the asset classes we can allow ourselves to invest in? And so on and so forth. So then what happens? And this is now the pipeline of the agents that are kind of proposing to put forward, goes as follows, like six steps. The first one, you have, let's say, a macro agent. So the macro agent will do what? We're basically looking to data, the economic regime, macro indicators, market indicators, and all this agent will come about is what is the economic regime? It's like an expansion, a late cycle, a recession, a recovery, associated with some confidence. And I think that's important because it's not about identifying a regime, but it's also about producing an assessment of the identification risk of that regime. Then you have asset class agents. So now what you end up having is to say, well, I have 20 asset classes or maybe 20 assets. U.S. equities, global equities or European equities, and then treasuries and corporate bonds and real estate and so on and so forth. I think they run an example of that model for March 2026. So I think they have 18 assets to allocate. But let's say you have a number of agents. Each of whom is given a specific task to focus on a specific asset class. And the main purpose is to come up with an expected return of the asset class of volatility estimate and some confidence around that. And then put forward an investment case like a memo for that asset class. Then comes a so-called a covariance agent, which is more of a, I would think of that less of an agent and more of a kind of an econometric or statistical tool that produces historical covariance estimation to bring this thing together. So now here we are having for all the asset classes some projection of return, you know, capital market assumptions, volatility and coherences, and you need to put this thing into a portfolio. What typically happens is that we have like no one or two portfolio allocation methodologies. Maybe we do some sort of invariance or some sort of a risk budgeting that's about it. Well, the suggestion here is to say why don't you actually allow the scale that agents can give you to run 20 portfolios. So there are now, actually there are 19, it's of whom builds a portfolio based on the previous inputs using different methodologies. And if I were to go through the methodologies, just for kind of naming a few, there's like five categories, the heuristics are more like no equal weighting, cap weighty inverse vol, and so on and so forth. Some are return oriented, like mean variance and black leader man. Some are more risk based, there is parity max diversification minimum vol. Some are as they call them non-traditional, like a civil optimization or like a TPA or drawdown constrained. And then the last category of all the portfolio agents has two agents, which are actually quite special. The first one continues doing research. So for the first 19, everything is almost like formulaic. I mean, there is later on, there are some tasks that they would have to undergo, but at least as a principle, they build portfolios, different portfolios that will make available to us. So the last kind of group or the last two are special. One of them is a researcher. So this researcher would just do some active research, perhaps look into the latest innovation in the portfolio construction space and come up with new ideas to design a portfolio that perhaps down the line can become like a permanent kind of agent, right? So for example, in this application, they have is maximum entropy. So this researcher is not finding maximum entropy as another possibility of building a portfolio. The last one, and I found that very, very interesting, is called an adversarial diversifier. So this is now an agent that observes the rest and effectively builds a principal component of the rest and tries to do opposite stuff. Now, why is that important? Because the whole aim is to build debate between them and get them to a place whereby the adversarial diversifier is trying to find pockets of correlations Dr. Esmat. have not actually identified. So now those 21 agents, what they end up doing post-designing the portfolios is that they assess the rest and they start voting between them. They make some point about, obviously, with that is computationally very efficient or expensive. And they say, well, we're going to force its agent to only vote for a peer that are in the same group and one outside of the same peer group. So eventually out of 21, you have 42 votes. The voting happens in a-- sorry, these are the reviews. Then they all vote to each other. And the voting is even more interesting. So every agent has to give six votes-- a five, a four, a three, a two, a one, and a minus two. And then there's another phase whereby all those portfolios because they have now a backtest based on today's composition as in third by the specific agents also have a composite score of sharp ratio, drawdown, and so on and so forth. So they try to basically score every agent now with the voting that comes from all the rest and a historical aggregate measure of performance. Those two, combined on a 60, 40 kind of scaling basis, give you the composite score of all the agents. So suddenly you have now all the portfolio agents being informed by the asset class agents who talk about the capital market assumptions and come up with arguments in favor or against who have already accounted for the macro regime. So I was like, you can see how one brings that next. And then you have the strategy review, which is this point of bringing together all those data points, and you have the CRO, that is basically the covariance agent, and then everything goes to the CIO. So CIO is an is a new agent here. And the CIO has to produce now a memo for the board that is going to condense all this information into a recommendation and some reasoning. And the interesting bit, and they show into some analysis, and maybe I should pause in a second for you to kind of start reflecting 'cause I know I'm keep on speaking now. In the example they show, if they were to run their model in March of '26, is that the CIO is actually getting a very different view to the voting mechanism between the managers. I'm sorry, between the agents. So the most popular allocation scheme in their example is not the most popular in the selection of the CIO. And this is primarily driven by the macro uncertainty and so on and so forth. All that to say that eventually, what they're bringing forward is that I'm kind of scrolling through my notes 'cause there's so many things I could actually talk about. All they try to bring forward is to say, with Gen AI, sorry, with an Agente AI, we cannot have scale. We can have some, as they call it, productive descent, which is about debating and peer-review. So between them using like natural language, they can interact. So third one is natural language audit trail. So if you were to go back and say, how fiduciary requirements are actually satisfied and deployed, there is a, I guess, an audit trail of those decisions. Then fourth, kind of composable expertise. You know, you put the specialists there, the CIO, some sort of forensic accounting modules and so on and so forth. And then it's called governable delegation. So you have the policy statement governing all the decisions how much risk you should take and so on and so forth. So to summarize, through all that process of agents, their point is human beings would do the analysis historically human beings will build the portfolios and so on and so forth. But the scale at which they can operate and the attention they can have is limited by the fact that we operate in real time and in human being capacities. Their point is that there's an element of supervision rather than replacement now, that should allow us to elevate the level of abstraction, guide the process with the policy statement that a human being would be writing and getting as the output from the CIO agent, the board memo for the actual board to then decide upon with an audit trail through to be fully auditable. Anyway, I'm posing here, there's so many things that we can go about, but that's the overall summary. - Yeah, it's very interesting, I'd scan through it myself and I mean, as you say, there's a lot of rigor to it and there's in the sense of applying multiple portfolio construction techniques that wouldn't be typical. I'm thinking in most investment committee processes, people maybe would use one or two or maybe a couple more, but you're not going through and even in the allocator series which I host and speaking allocators who go through the process, they might say, I spoke to one recently, so I think it was three different portfolios, but here they're producing, I don't know, 15 or 20 effectively. I suppose what I'm curious about is what elements of the process is the outcome most sensitive to, from the perspective of obviously, in this example, as you say, the run it in March of 2026, and from a macro perspective, they concluded it was late cycle with some stagnationary risks, which I guess refactors, obviously, what was going on in energy markets at that time, so that made sense, so that's one thing, and then obviously you have the behavior of the CIO agent. As you say, he tilted the allocation towards portfolio construction techniques that the agents didn't really vote for, but they were also relatively plain vanilla techniques from memory, the ones at the highest allocation, so I didn't get enough detail or I didn't understand what drove his decision. So I'm kind of wondering that, obviously, there's not a regular there, but ultimately, what really drives the tilting, and in this situation, the benchmark was 60/40 portfolio, and I think we came out at 44% equity, so it came out with relatively meaningfully underway equities, maybe the macro regime was part of it, I don't know, obviously portfolio construction was a bit, because they come up with capital market assumptions, and they have a mechanism, so I suppose that ties to the macro regime, so they, obviously they put less emphasis on historic capital markets, returns, and more on, I guess, forward looking estimates, so yeah, that's a bit, and the insights on that, or how do you think ultimately that 44% that underweight equities, what did that stem from, would you say, reading the paper? - Yeah, I mean, it's not very obvious how it comes about, because it is ultimately a combination of weighting schemes of different portfolio mechanisms. I mean, my gut feeling goes as follows, and that's abstracting a bit from an or the abstract context here. I mean, ultimately, the way we do asset allocation is not just informed by risks and coverances and capital market assumptions. I think the other statement I would make is our ability to now cast, if I were to use the term we used that era, to now cast the economic environment in a very accurate manner. Then I think we are more prone to build some concentration in our portfolios. When the economic regime is more mixed in terms of evidence and data points to categorize it in some confidence, we typically vouch more for diversification. I mean, perhaps it's a very similar comment by in a very different context to the one I made earlier on about the following, like a reframing a model to give you a better estimate of what is ultimately unobservable, the current regime, ultimately still bears the risk of the model being wrong and the allocation being incorrect and ultimately leading to a loss. And I pose the question here, should we instead be more prone to diversify at the time that we cannot tell how the macro outcome is clear? So if it's more unclear, then we should vouch more to our diversification. So kind of going back now to the paper and your question, my gut feeling is that the mix of contradicting macro signals at the time and the fact that it was like a stack flation and like a late cycle type of a period, perhaps suggests a location that is less driven by a capital market assumption. So I think the allocation that the CIO goes for is less informed by a return oriented allocations. So like cap weighted, vol targeted, equal weight universe variance, these are like some of the higher ranked portfolios that the CIO chose, which do not contain any capital market assumption. These are going to risk based allocations. So in my mind, it's more like, I'm not trusting my capital market assumptions because the regime is not very clear. And because it looks a bit fluffy, I should then rather tilt my allocation towards risk-oriented and more heuristic allocation frameworks rather than trusting the data as much. That's my kind of gut feeling or maybe my interpretation. Yeah, yeah, that makes sense. I mean, they end up with a more conservative portfolio for the first four percent equities, which is interesting. I mean, one other thing that was interesting that was comments upon in the paper is how, you know, it's very hard to do a back test. I mean, that's the most interesting for me to have a back test, LLMs, because they all currently incorporate information now that they wouldn't have had back running it in real time. I mean, they do point out that you could, some researchers have tried to limit the LLM models to use models that were only available at a point in time, but it sounds like that's not, well, maybe those ones were even computationally strong enough at that time to run these types of analysis. So, yeah, I mean, it takes, you have to kind of take it, maybe at base value, the merrier is a bit, or I mean, as researchers then, how do you deal with that? If you can't back test, how do you evaluate? So, that's an amazing question. And I mean, that's why kind of reading it through, put me into a lot of thoughts, because there's a lot of forward-looking biases, and they fully disclaimer, so the discussion actually very nice, that is look ahead by us, by the way, in a variety of ways. The first one is the obvious that you're using a model that was built today, perhaps to build estimates for yesterday, so it has all the information baked in the model, and even if you were to contain the data as of when, the model still has the ability to, or at least has the knowledge in its parameterization of the future, even if you contain the input. The second part is, at the time that they start kind of voting between them, which one is the better model and so on and so forth, then we have the typical look ahead bias, or maybe data mining bias that we always have in back testing. If I look into back tests, most likely I can choose the one that looks better, so I would imagine the agents themselves having like no 20 portfolio allocation schemes between them, perhaps they start kind of voting more in favor of the better performing one. So it's almost inherent now in the process, what historically has been human beings kind of assessing back tests. So these are two considerations. The other consideration which I find even more interesting and I guess challenging from your perspective is LLM models are not deterministic, and even with the same model, with the same prompt, you might end up having a different answer. So a reproducibility is nowhere to be seen with this type of models, at least as it stands, which in itself creates significantly harder task for someone not only to build a back test, but suggesting that this is representative of the methodology because it is not. Like even with all the rest being solved then and say today we start, we start building a back test as of today, so tomorrow we're gonna have a new model and we're gonna do the same thing. So like we come here in a year from today, you and me, we have the same conversation with the year of a back test, how do we run history or how do we ask the model twice at the same time, a similar question with a slightly different prompt, we will have gotten to different two different back tests. So I think that's the other challenge. Setting that aside, I mean, if you are the points that they make by the way, just looking through my notes, you might also have issues with regards to the fact that using the same LLM model, they call them monoculture risk. So if all agents follow the same model from one of the big kind of GNI kind of companies, you might find yourself being exposed to some correlation in the model, so that's another interesting one. But overall I think what I find interesting is the fact that there is here some suggestion that I would imagine can inform more accurately and more holistically asset owners. We cannot negate the fact that having the power of parallelizing all those tasks and creating better estimates of maybe the macro regime or the capital market assumptions or portfolio construction details, at the minimum, should get us and investment boards more informed. So in this regard, I think there is value, in the architecture of it, I think there is value, and above and beyond, I think the perspective is quite interesting. Just if you were to take this framework and obviously it's applied from the perspective of longer term asset allocation, multi asset portfolio construction, but at the end of the day, it's still building portfolios. If you were to apply it to building a trend portfolio, is there anything that you learned from the paper or anything that you thought, okay, that's something that would be implementable in the near term? Yes, so I think some parts are actually quite interesting because let's go back to this kind of food chain or workflow. So let's assume you're building a trend model and you tried to feed it into those steps, okay? So you have a macro agent that says, okay, what is the economic regime? What does the trend follow? Well, I don't care about the regime, but if the price goes up, I'm going to buy. And obviously, the fact that I observe in my price is nothing more than an indicator of the regime, like equities you'd belong more often than not when growth is there. And by the way, that's what economic trend does at the end of the day. You're looking into a regime and then you infer that your regime estimate is correct. So you buy the asset that's performing the regime. So pocket number one is our signal. Then asset class agents. So which is the expected return and the volatility of which one of those markets that we have? Or what is the confidence around that? Well, I guess when we do trend following, we say the expected return is our past return, maybe skilled by some measure of all or whatever. So in a way, the confidence we have is how much volatility is, which shrinks or expands our forecast. And the magnitude is coming purely by how strong that trend is. And these are not compatible. The same way as capital market assumptions are. So that's step number two. So the signal in, I guess, one and two are kind of similar, but I guess the macro agent would look into predictors of performance, whereas the asset class agents more about the relative strength. The CRO, we do it, it's the covariance estimation. However, you want to estimate your covariance with the variety of techniques to make it robust. The fourth with portfolio construction, this is the place that typically we go for one or two. That's about it. So I think here there is something that somebody could spend some time on and looking at. Now how that then flows into an investment decision in the current framework is about all this core mechanism. And you know, with portfolio favors there, so the portfolios and how they change their assessment of their peers, not clear to me how that comes into trend following. But it's not that those steps are too abstract to how typically operate in their research environment. That's why I found it quite interesting because I can see as the researchers, going through those steps, sometimes consciously, sometimes subconsciously, to eventually go from road data to a strategy, to a single line. I mean, is it fair to say with the evolving, emerging technology, you know, that if you're trying to satisfy a portfolio for multiple objectives, that's maybe easier now. I'm just thinking, in this example, obviously they had an IPS and I think, you know, is relatively simple, you know, objective or whatever it was, sharp maximization or a certain return for certain vol. Obviously, if you're a trend follower, you're trying to generate absolute return, but you want to tilt the portfolio to first crisis alpha or performance in the downturn, you want to minimize drawdowns. Yes, yes, yes. All this can come into. Multiple objectives. Correct. Correct. Yeah. At times conflicting. At times conflicting, or at times, yeah, I mean, hard to define, you may have more objectives than are just defined by mean variance optimization, as well, that's the point, I guess. Does that become easier now, and this kind of framework, do you think, are not? I mean, I think it becomes more accessible, let's put it this way. You would still have to, I would imagine, to utilize, you know, the expertise of running those portfolios to present something that is both sensible, as well as tractable. Because, ultimately, those decisions are made by human beings and investors. I see some investors that hold their responsibility over running the those portfolios. But I think we'll make it more accessible, just to be clear. The first paragraph of the paper is actually quite truthful. I'm reading through, as you were speaking, it strikes me that basically what you're saying is in this paragraph, it says, "The most binding constraint in asset management is not data availability or model sophistication." We can get the data and we can be sophisticated enough. But it is the finite bond with of human decision-makers. And then they go about talking about a CIO that perhaps can oversee 10 to 15 departments that are organized in lines of asset classes. And then a fundamental analysis can probably cover 10 to 20 stocks. And a committee that is kind of coming together in a month or quarterly, sometimes for a few hours to just say, "Okay, let's go and see you coming in the next committee." Like it reminds me, actually, of a client that said around the inflation regimes in 2022. Why trend following is useful? Above all empirical data points, it is going to take opportunistic shorts or longs, depending on where you are, without expecting the next investment board to say, "Okay, let's change the allocation." So it was purely an attempt to shrink the time that it takes between a decision and deployment, which is a limitation in the way that institutions operate, just because time is finite and it kind of ticks deterministically, but it takes time in this way, right? So one of the arguments was we like trend following because it can be opportunistic and deploy the exposures faster than our ability to bring together the investment board, do the analysis because by the time we do that, it's already gone. Yeah. Interesting. I mean, one final one, I mean, obviously we have, you know, in our world programs built by machine learning. I mean, this is framed so little differently with distinct agents operating in very well-defined capacities. I mean, how soon do you think we will see products in the market that are clearly labeled as run by AI agents? Hard to foresee, I think the asset management industry can utilize, I would imagine, those technologies. I mean, we all can utilize the technologies, but in our side, obviously designing index products. Yes. You know, the bar is higher for the obvious reasons. I think the reason why this is different to just utilizing historically coding and back-testing platforms is that the agent is ultimately speaking with its peers in natural language. Exactly. So we can then go back and read and understand and check the debate and this is all becoming much more auditable and tractable, but that in itself is stochastic. Yeah. It's not X plus Y equals to two if X equals to what is my Y. And I think that's the beautiful challenge in this regard, but the benefit of the agent that it speaks the language rather than just running the math. Interesting, yeah. We're definitely awake up cold as to, you know, how far things have come along in terms of putting not just, you know, the use of AI, but multiple agents together. And as you say, when they're speaking to each other, and some of the additional benefits to come with that in terms of an audit trail, et cetera. And so I think, yeah, it's definitely, it doesn't get you thinking as to what's coming next. But let's leave it there for today. Thanks very much, Nick, for bringing those research topics and always fascinating to get your thoughts. And Neil, there's a way next week again. So I'm back again next week speaking with Jim. So if you have questions, please send them in. But Nick, thanks for coming and to everybody out there, thanks for dialing in and we'll be back soon with more content. Thanks for listening to Top Traders Unplugged. If you feel you learned something of value from today's episode, the best way to stay updated is to go on over to your favorite podcast platform and follow the show so that you'll be sure to get all the new episodes as they're released. We have some amazing guests lined up for you. And to ensure our show continues to grow, please leave us an honest rating and review. It only takes a minute and it's the best way to show us you love the podcast. We'll see you next time on Top Traders Unplugged. This podcast expresses the views of its hosts and the guests appearing on the podcast as of the date of its recording and such views are subject to change without notice. Top Traders Unplugged do not have any duty or obligation to update the information contained herein. Furthermore, Top Traders Unplugged make no representation to its accuracy and it shall not be assumed that past investment performance is an indication of future results. Moreover, wherever there is a potential for profit, there is also the possibility of loss. This content is made available for educational purposes only and should not be used for any other purpose. The information contained in this podcast does not constitute and should not be construed as investment advice or an offer to sell or a solicitation to buy any securities or related financial instruments from its in any jurisdiction. Certain information contained herein concerning economic trends and performance is based on or derived from information provided by independent third party sources. Top Traders Unplugged may believe that the sources from which such information are obtained are reliable. However, Top Traders Unplugged cannot guarantee the accuracy of such information and has not independently verified the accuracy or completeness of such information or the assumptions on which such information is based. This podcast, including the information contained herein, may not be reproduced, copied, republished or posted in whole or in part in any form without the prior written consent of Top Traders Unplugged.