Unsustained sales growth and AI

 

We are seeing very strong expectations for AI sales growth. There is no question that new technology will see stronger sales growth than the average firm and that, during the initial growth period, sales may be well above average. The question is, how do you temper these sales expectations to form more realistic estimates? The power of compounding will work against you. You can, of course, rely on some form of mean reversion, yet this can be guesswork.  

This problem was addressed in two papers by Counterpoint Global - Bayes and Base Rates: How History Can Guide Our Assessment of the Future and Bayes and Base Rates 2.0  I like this work because it takes the emotion out of the sales forecasts associated with AI and focuses on what we know across decades of data, within different industries, and with major changes in technology. We can form base rates using priors and then derive normal forecasts. The conclusion is that the sales forecasts are just too large, even if we isolate new technology, focus on specific industries, and account for the very best historical events. 

This does not mean investors should short these companies. It is unclear when reality will be realized, but arriving late is problematic, shorting can be a fool's game, but buying on these aggressive growth forecasts will be disappointing.  

The time series of risk shocks

In an earlier post, we discussed the differences in risk regime through decomposing the VIx index. 

The time series of risk regimes

We can also do the same for risk shocks, which are measured by changes in the VIX. We use bin analysis based on quantiles to form three groups of risk shocks. 

Again, a simple null hypothesis is that risk shocks occur during periods of market extremes, such as recessions and market turning points, yet we find that the time series of changes in the VIX, or risk shocks, appears more random. 

There is a different market response to risk shocks than to the risk regime; more simply, positive changes in the VIX index are associated with large market downturns, but their clustering differs from what we see in the risk regime.

The time series of risk regimes

The VIX index has been used as a fear index, but we believe the best way to view it is to define risk regimes. There are periods of normal, high, and low risk and the behavior of markets during periods of high risk will differ from periods of low risk. Before we start examining the market response to different risk regimes, we should examine the time series of risk regimes and determine when high- and low-risk regimes occur. 

A good null hypothesis is that market returns are independent of the regime. We assume there is no relationship. However, we do expect there is a trade-off between risk and return. The market will react to risk, and the reaction should be stronger for high-risk regimes.  

We take a long time series of monthly VIX returns and divide the series into quantiles, with the low risk being the lowest quantile, the middle range being the next three quantiles, and the high risk representing the highest VIX value quantile 

We find that high equity risk will coincide with turning points in the stock market. Specifically, a high-risk regime will be associated with recession and drawdowns in equities. There will also be low-risk clusters, and these are associated with higher return periods.

Returns respond differently to high-risk periods than to low-risk periods. This is a piece of ongoing research we are focusing on. 

EU Geopolitical risks - different from Anglo geopolitical risk

There has been a boom in indices that measure risk by analyzing news story words, yet not all news is created equal. There can be big regional differences, and recent research shows that geopolitical risk measures in one region may not align with or accurately reflect those in another. The recent research paper, Geopolitical Risk in the Euro Area: Measurement and Transmission, shows that there are differences between EU and Anglo geopolitical risk. Clearly, some events are more important to Europeans. We can see this in the residuals from a simple regression. The more recent history shows a strong divergence in risk. There are also clear spikes in the daily data that indicate European risks differ.

The risk differences have clear macroeconomic effects. European geopolitical risks show a stronger influence on industrial production and inflation.

Causal inference and critical statistical thinking

Causal inference is one of the most important topics in finance today. There is a difference between what correlates with or is associated with X and Y and saying that X causes Y. We can thank the work of Judea Pearl for truly focusing our attention on causality rather than correlation. 

You should not ask what tends to happen to Y when X is high. Of course, you can ask, but that only refers to the association. The real question for causality is, "What will happen to Y if we set X to a specific vlaue and all other factros are held constant?". To answer that question, we have to consider the relationship between X and Y, and also ask what other factors may influence Y, such as variable Z. Does Z cause X, which then affects Y? Does Z affect Y directly? This type of thinking is not about fitting a set of past data into a relational model, but about asking the primary question of whether there is a reasonable link between these variables. 

Before you run a statistical test, think about causal relationships and how they may be linked together. What type of relationship are you trying to find? 

Hedge fund strategy rebound

 

There has been a strong rebound in hedge fund strategy performance in April after poor March returns. All the HedgeIndex Main strategy returns were positive for the month, with especially strong performance in emerging markets, global macro, and long/short equity. Of course, the overall equity market showed strong April gains, so the market exposure for these strategies provided a tailwind, and positions placed at the end of the market were able to take advantage of the stock market improvement despite the continued uncertainty associated with the Iran War.

Commodites versus stocks - Go with the real economy?

 

The power of supply shocks and the real economy can be seen when we compare the BCOM with the NASDAQ and SPX. Since the beginning of the year, there has been a strong acceleration of commodity prices. This momentum was even before the Iran conflict. A combination of strong demand and a supply shock has been driving the commodity market, even amid all the buzz about AI. Of course, AI is driven by electricity (energy) and infrastructure (metals). 

So ends the view that inflation is tamed

 

So ends the view that inflation is tamed and rates should fall. The PPI is accelerating and moving back to the type of supply shocks that we saw post-pandemic. The CPI is also heading higher and moving further away from the target with a 3-handle. There is no room for a Fed rate cut, and with real rates now near zero, there is a strong case for a rate increase. 

We do know what the Fed hates - supply shocks. Monetary policy is a tool that is not built for supply shocks, yet here we are.

Why nothing works - We cannot decide whether we are Hamiltonians or Jeffersonians

 

Why Nothing Works: Who Killed Progress and How to Get It Back by Marc Dunkelman is one of the more interesting books on politics that I have read this year. It is thought-provoking and can help explain the problem in getting things done in the US. It may not solve the problem, but it offers a plausible framework. 

The progressive movement, now well over 100 years old, is driven by conflicting philosophies about the role of government. These two approaches, Hamiltonian and Jeffersonian, represent very different views on how government should be used to solve problems. The Hamiltonian approach is a top-down, big-government approach that seeks to offset large private-power and control projects through experts. The Jeffersonian approach to government looks at large institutions and power as corrupting. The power should be dispersed and controlled by the people, not by experts or large institutions. 

How can you get something done if top-down control by Hamiltonians is viewed with suspicion by the Jeffersonians? You may not be able to have ot both ways, and vacillating between the two will lead to inaction and program failure. The train to nowhere in California is all about the Big project, Hamiltonian government micromanaged by Jeffersonian rules and regulations to get local input. 

No one seems to want either extreme, but the middle ground leads to an environment where Nothing works.

The Doom Loop - Explaining the dollar

 

The Doom Loop: Why the World Economic Order Is Spiraling Into Disorder by Eswar Prasad is a good book for explaining the current trouble with a dollar for anyone who wants a non-technical read on the subject. It focuses on the intersection of economics, finance, and geopolitics rather than on the theory of international finance. 

The book’s main focus is that we are caught in a destructive feedback loop driven by a changing geopolitical environment. The movement away from US hegemony in globalization is now being replaced by a fragmented system with more dispersed economic and financial power. It is not that we should go back to the old system, but globalization caused fissures that cannot be replaced. The backlash to a global hegemony of rules and governing institutions means that a single currency cannot dominate the world and create a stable world order. 

Can the dollar be replaced? The answer is no: the dollar cannot dominate, which means there will be more financial instability in a world order that cannot be controlled. 

What are equity markets discounting? it is not risk

 

The Iran conflict is not over, yet the markets are optimistic. Perhaps it is because we don’t know what to call this oil crisis. Is it a war? A dispute? A current pause? The SPX was up over 10% for the month. The high beta names were up over 15%. For the sector extremes, the communication services sector was up over 18%, while the energy sector was down 3.45%. Surprisingly, emerging markets were also up over 11% for the month and strongly higher over the last 12 months at 32%.  Even bonds were slightly higher for the aggregate index.Yet the market is facing a significant commodity shock, with the DJCI up 31% so far this year.

Is there anything to worry about? Central banks? Growth? Inflation? The markets are either looking through any negativity or do not believe it even exists. This is a path that should concern any investor. 

Periods of Stagflation - there have always been with us

Despite strong performance in equity markets, there is still considerable talk of stagflation. The stagflation story is not just a 70's problem. It can happen in other countries and almost any time. It is more likely that we have a supply shock that can affect both prices and growth. The longer the oil crisis in the Middle East lasts, the greater the likelihood that we will see stagflation. Stagflation has generally been short-lived because the underlying cause changes. An energy crisis is averted through a new supply or a solution to the initial problem. 

Right now, we are not close to the 2% inflation target, and the cost of higher energy is just starting to bite. The likelihood of a stagflationary period in the second half of the year is increasing.

Risk aversion index worth a look

 

There is a growing number of risk measurement indices, although the definitions of these risk or uncertainty indices are not always clear. We can start with the VIX index, which is not really an uncertainty or risk index but a proxy for option volatility and is often called a fear index. There is a set of policies and economic indices, derived from news scraping, associated with countries and topic areas.  

Another entrant to this field is the risk aversion index.

The general estimation philosophy is as follows:  

​

(1) The risk aversion coefficient is utility-based, reflecting the time-varying relative risk aversion coefficient of the representative agent in a generalized habit-like model with preference shocks.                                                          
(2) Given the no-arbitrage framework, asset prices, risk premiums, and physical/ risk-neutral variances are exact functions of the state variables, including risk aversion, in the dynamic (exponential) affine model.

(3) Financial variables are observable. Thus, the market-wide risk aversion should be spanned by a judiciously-chosen instrument set of asset prices and risk variables. We use the Generalized Method of Moments to estimate their optimal linear combination given asset moment restrictions that are consistent with the dynamic no-arbitrage asset pricing model. The instrument set includes a detrended earnings yield, corporate return spread (Baa-Aaa), term spread (10yr-3mth), equity return realized variance, corporate bond return realized variance, and equity risk-neutral variance. 

I find this risk aversion index fits the story expected when there is higher uncertainty, and could be worth following as another indicator of changing behavior in financial markets. 

Trading with signal and price impact uncertainty

 

When you want to make your model practical, you have to look at signal uncertainty and price impact. If you use any model, your one-step-ahead forecast may have some uncertainty because the average coefficient may not accurately represent the true coefficient sensitivity at a given time. Similarly, for any model there is going to be a prcie impact from trading. If the signla is weak then iapct uncertainy is not that important but as the siganl strengthens, the effect price imapct will become more important. See “Trading with uncertainty about signals and price impact.” These real-world effects are important if you want to trade a model.  

Expectation Bias and short-term Momentum

 

Machine learning can be used to predict analyst forecast errors. These forecast errors can predict cross-sectional returns and abnormal returns. There is an underreaction to fundamental news, which is amplified by overconfidence, sticky beliefs, and information uncertainty. This expectation bias can explain short-term price momentum in high volatility stocks. From expectation bias comes a rationale for trading patterns in price. See "Expectation Bias and Short-term Momentum". Past forecast errors have a critical impact relative to other features.

Attention versus earnings and momentum

 

One area of increasing research is the attention that is given to a specific market. Investors cannot follow everything, so there are different levels of attention. Given changing attention, there should be different levels of efficiency. What is found in the paper, "A Tale of Two Anomolies: The implications of investor attention for price and earnings momentum," is very interesting. Stocks that receive more attention exhibit greater price momentum and weaker earnings momentum. The authors make the following claim: investors pay less attention to earnings news, stock price underreacts, leading to stronger earnings momentum, but when attention is high, behavioral biases intensify, which fuels overreaction and price momentum. Depending on the type of attention, the effects will vary. 

Multi-agent LLM systems for profit

 

LLM can be used to develop autonomous trading systems. The key is to have agents mimic the workflow within a multi-agent trading framework that divides a trading system’s tasks. When you look at a deep decomposition of the tasks associated with a trading system, you will get better risk-adjusted returns. In the paper, “Toward Expert Investment Teams: A Multi-agent LLM System with Fine-Grained Tradign Tasks”, the researchers develop what they call a fine-grained system that looks at detailed tasks and instructions and compares it with a coarse-grained LLM system that does not provide detailed instructions to the agents. 

Across different stock portfolios, the fine-grained approach performs much better. It is notable that we can examine the effects of dropping specific agent tasks and assess their impact on the Sharpe ratio.

The results are clear - be detailed with the LLM tasks given to agents. The more specific you get, the better the results.

Mimicking managers for profit? Not so fast

 

Portfolio managers can be viewed as economic agents that have regularized behavior. Hence, if we can formulate that agent’s behavior. That is, we can mimic their behavior. If that is the case, we should then be able to generate a portfolio with similar returns. This is what is done in the paper, “Mimicking Finance”. The authors in this paper use AI and ML to extract and classify the behavior of economic agents that is predictable from past behavior. The agents may view that their behavior is novel. It is not. A large percentage can be mimicked, with approximately 70% of mutual fund managers’ trade directions predicted. The more history we have about a manager, the more likely we are to predict their behavior. Managers who oversee many funds exhibit greater predictability. But, it has been found that higher ownership leads to less predictability. 

So why do we need portfolio managers? We can just develop agents with different characteristics to do the job. There may not be that much special with many managers. This really shows the power of AI within the asset management world. However, we may have to step back with some conclusions.

Interestingly, managers whose behavior is more predictable significantly underperform their peers, and those who are the least predictable do better. If you cannot be typecast with your behavior, or you are changing your behavior, you will do better. 

The morning volatility uncertainty effect

 

There has been an increase in research on what happens between the close and the open, and from the open to the close, in asset markets. In the equity market, significant differences have been found between overnight returns and daytime returns. 

In the paper, “Early Birds Get the Vol; Morning Volatility Uncertainty and Variance Risk Premium”, the authors find that the volatility of the VIX or VVIX at 10 AM EST can strongly predict the next day’s asset return's variance. The authors mine the day to show that there is a significant risk premium that can be exploited. I have reservations about the results, but I’m interested in the finding that volatility shocks have a spillover effect on volatility the next day. 

Volatility shocks will have spillover effects that can be exploited. 

Can market forecasts front run information? The answer is yes

 

The foundation of market rational expectations is that a scheduled report cannot affect the firm’s stock price until it is reported. You can’t act on information you do not have. Yet, the paper “How markets forecast and ‘front run’ Information: Bayesian Market Efficiency” tells a plausible story that can explain some key market behavior.

The argument for this front-running is based on Bayesian statistics. Assume there is a Bayesian investor who, rather than waiting, infers what will be in a report before the release. Given this inference, the Bayesian investors will reprice the stock before the announcement. Yet there remains uncertainty about the content of any news that could lead to a rise in premiums, particularly regarding the precision and quality of the firm’s financial reporting. The premium can be either positive or negative. Hence, the stock price and the cost of capital will be impacted by how well investors can form expectations about a given financial report. 

It seems this already happens in markets. Investors form expectations about what a financial report will say, and those views are incorporated into the price. The Bayesian approach provides more structure to how expectations are formed. We are all Bayesians, so saying that we form rational expectations does not really tell us much about how expectations are formed in real life. Using Bayesian updating provides structure around our behavior.

Decoupling dollar and Treasury privilege

 

When we think about the exorbitant privilege of the US markets, the question should be divided into two parts. The Treasury privilege is associated with financing at lower rates than in other countries and with the dollar’s use across the information finance landscape. They are not exactly the same thing. 

The paper "Decoupling Dollar and Treasury Privilege" shows a difference in the convenience yields between Treasuries and the dollar. The convenience of the dollar is measured by the covered interest rate parity (CIP) between risk-free bank rates, SOFR, and the convenience yield of treasuries, which is captured by CIP deviations in government bond yields. There has been a divergence between these two convenience yield measures. 

The dollar convenience yield exists in the post-GFC period, while the convenience yield for Treasuries has turned negative, especially for longer maturities. The authors argue that this change in Treasury yields is related to the excess supply of Treasuries. This sends a clear warning that the US Treasury cannot finance debt at the current rate. 

Do LLMs make market more efficient? Yes

 

We have seen an explosion of new papers on how to use LLM in finance. Clearly, computing power can enable analysts to use vast amounts of data more effectively across companies. Many papers have shown that excess returns can be generated by using LLMs, but a more fundamental question is whether markets have become more efficient since the introduction of LLMs. This is the focus of the new paper “Do LLMs make markets more efficient?". 

The answer to the question of efficiency is yes. LLM availability eliminates 40 - 60% of post-new drift into the next trading day. LLM helps with short-horizon price discovery. The researcher used a novel way of determining this value-added by examining the effect of plausible exogenous outages of major LLM providers. When LLM providers are unavailable, there is more drift. 

Get on the LLM bandwagon, even though markets have already become more efficient with the use of this tool.  If you are not usng this tool, you are falling behind competitors.

False discovery rate in finance - Thinking out of the box

 

Aha! I found another risk premium. This has been the mantra of finance for well over the last decade, yet perhaps we should comment, "not so fast." While on the one hand, there has been an explosion of research finding new factors, what has been called the factor zoo, there has also been pushback by other researchers who have pointed out the issue of data mining. The argument of data mining is that conventional inferential frameworks are inappropriate when there are endless tests of different model specifications before the right one is reported. We will mine the data until we find the right result. Other researchers have pushed back against the data miner, with analyses showing that the posterior-expected alphas still exist even after the initial results were reported.

A new paper. "The False Discovery Rate in Finance: Identification failure and search-adjusted estimation" outlines how this problem can be solved. There should be a search-and-selection process for identifying factors. Knowing that process will help detect the false discovery rate, but if this search mechanism is unknown, there will be a greater likelihood of underestimating the true false discovery rate. 

Using some lower bounds calculated from their work, the authors suggest that most reported discoveries in finance are likely false. Ouch, that is a strong indictment and has strong implications for academic research and the work of quants who use that research to develop profitable trading strategies.  

Narrative and macro investing

 

An exciting area of macro research is the use of narrative to help explain the weekly movements in equity markets. This work is still in its infancy and seems to be taking several different directions. This work on narratives started with Robert Shiller and his research on narrative memes that may create bubbles. Another analytic approach has been the development of indices that attempt to measure risk by counting mentions of news events. It has expanded with the development of NLP and LLM models.

An interesting application has been developed using the GDELT database to create different narratives. These narratives are then used as input to a macro model that uses key economic data from FRED. See the paper, “Monitoring Narratives: An Applicaiton to the Equity Market" Using a set of key narratives developed around news themes, the authors find that added narrative information will increase R-squared and reduce error for a model trying to explain equity returns. 

This paper scratches the surface, but it does provide an interesting link between narratives and fundamental data to help explain equity returns. For all the focus on macro quant data, story-telling is still an important driver of markets.

Rationale for trend-following updated

 

The case for trend-following is well established, yet, given the fluctuations in returns during periods without a crisis, it is worth revisiting fundamentals and discussing the rationale for this hedge fund strategy. Meketa, the pension consulting firm, produced a white paper on the topic at the end of the year that provides some new insights. 

One, the dispersion between trend-following fund returns is significant. The difference between the best and worst can be over 25%, and the difference between the 25th and 75th percentile averages around 10%.

 

Two, the difference in dispersion will increase with the extremes in equity returns. When market dislocations are greater, there will be greater dispersion in returns. 

Three,  the Sharpe ratio can be smoothed and increased if an investor chooses a portfolio of managers. It may be hard to say what the right number is, but 4-6 seems to provide the benefits of smoother Sharpe and less dispersion in the return-to-risk trade-off