Debiasing decisions - Some simple rules to follow

We all face biases or bring them to decision-making, so it is critical to develop strategies to reduce the risk of bias. The bias problem applies to both quantitative and discretionary decisions. Just because you are using a model does ot mean that you are immune to biases. There should be a checklist to review the potential impact of biased thinking. The paper “A user’s guide to debiasing” does a good job of exploring the basics of reducing biases and improving the quality of judgment in decision-making. Debiasing reduces logical inconsistencies and misperceptions or misjudgments of reality. Debiasing is not the same as gathering more factual informaiton. The objective is to improve decisions given a specific set of information.

Categorizing debiasing methods distinguishes between the person and the task. Improving the person requires training to help the decision-maker overcome their limitations. The second approach is to modify the environment to match the thinking required.

Many of the sources of our biases come from the confusion between system 1, fast and automatic responses, and system 2, which requires slower and more deliberate thinking. It is important to distinguish between narrow thinking and shallow thinking. Narrow thinking focuses attention on a single category of objectives and crowds out the ability to identify other alternative objectives. Shallow thinking devotes too little effort to the required task. For any decision, there has to be a level of readiness to perform better decision-making. 

The person can be modified through better education that generates more alternatives, tempers optimism, focuses on improving judgmental accuracy, and assesses uncertainty. Decision-makers can use defaults to get closer to making better decisions through regular processing, nudges to induce reflection through prompts or planned interruptions, and the formation of a set of active choices. If this can be done for the individual, a similar process can be applied to the organization. 

AI - all the time for business

 

You have to love some of these charts that bundle ideas that seem to be unrelated. In this case, we find that the word "AI" is used more often on earnings calss than the word "earnings". We should expect that the word earnings is fairly static on earnings calls, but the explosion of the word AI suggests that this is the what management and investors have as their main focus. For management, using the the word AI convesy what they are doing new to address issues of tehcnology and effciency. Investors want to know how firms are using new technology. The question is whether AI will actually lead to the efficiency gains that many expect.

Decision focused learning and portfolio selection

One of the more interesting papers on portfolio management links prediction with optimization. Rather than a two-step process, the authors focus on how optimization should be managed alongside prediction. The paper, “Return Prediction for Mean-Variance Portfolio Selection: How Decision-Focused Learning Shapes Forecasting Models”, provides insights on how decision-focused learning (DFL) can be used to improve overall portfolio returns. 

The usual process for building a portfolio is through mean-variance optimization. This process is two-staged. It is a predict-then-optimize method. In the first stage, a set of expected returns is generated, and in the second stage, the optimization selects the set of assets that maximizes return subject to a set of constraints. The problem with MVO has been studied extensively. The issue is that if the expected returns are poorly defined, the MVO will choose the “best" returns, yet the portfolio may be optimized on the forecast errors. The classic answer from Markowitz is that estimating expected returns is the investor’s job, not the optimizer’s.

The DFL framework will integrate the prediction and optimization to improve the outcomes. The issue is whether the MSE of forecasts for each asset is treated independently and equally or integrated with asset correlations. With DFL, the optimization accounts for prediction errors when finding the weights via a loss or regret function.

It is found that DFL identifies fewer assets than a standard MVO and exhibits a bias toward positively returning assets, given the optimization for a long-only portfolio. Still, it offers a better way to optimize a portfolio.

Price action by Rhetoric: Trump and Oil

 

The FT chart provides an interesting insight into the drivers of the current oil market. Of course, oil is driven by the events of the Iran War, yet the impact on oil prices is more subtle. There seems to be a direct connection between President Trump's comments and the surge or decline in oil prices.  When Trump makes comments that escalate tensions, usually before or on a weekend, there is a surge in prices, followed by comments that de-escalate tensions. The uncertainty in prices is associated with rhetoric rather than specific action surrounding Iran. The sample is small yet there may be a link between comments and oil price action. 

Dual role of prices - endogenous and exogenous events

 

...dual role of prices. By “dual role”, we mean that prices not only reflect the underlying economic fundamentals, they are also an imperative to action. That is, prices induce actions on the part of the economic agents. If some actions are the consequence of binding constraints and exert harmful spillover effects on others, then price changes can bring about amplifying spillover effects that disrupt the smooth working of the market, and sometimes shut down the market completely.

Endogenous Extreme Events and the Dual Role of Prices

It is important to appreciate the dual role of prices, although this is a subtle concept. Prices first reflect exogenous events as markets reflect new information that impacts expectations. If inflation increases, for example, there will be a reaction in prices as investors adjust their expectations. However, investor will not just react to new information and adjust their portfolios. They will also adjust or take action when they see prices change. 

The reaction to price movements may be independent of the change in exogenous information. The reaction could be due to uncertainty about what information is being displayed in the price. A reaction to price behavior independent of exogenous information is an endogenous reaction. Investors react to prices rather than to any other information. This can lead to extremes and explain most of the price movement during the day. One of the most important tasks for an investor is understanding the difference between these price moves and appreciating the action that stems from the distinction between exogenous and endogenous moves. 

Neoliberals and the fight between dominium and imperium

 Quin Slobodian’s book Globalists: The End of Empire and the Birth of NeoLiberalism was written before the pandemic and before the uproar about Davos and the World Economic Forum. Yet it is truly relevant to anyone considering the current world order between some form of global government and nationalism. Globalist does a good job of describing the origins and rise of neoliberalism and helps readers understand the differences from national movements or a national focus. 

What I found most interesting was the focus on differences between dominium and imperium capitalism. Dominium refers to the rights of owners to control their property, which is a key feature of capitalist private property. The imperium or public power refers to the sovereign power of the state to rule, tax, and regulate. The intersection between these two forms of capitalism is the crux of how neoliberalism bears on the issue.  

For Slobodian, neopliberalism is not a simple version of laissez-faire capitalism, but a project to, as he terms it, “encase” the market within legal and institutional frameworks to ensure that dominium is protected over imperium. Global capital is protected from democratic pressures, nationalism, and social redistribution that seek to take property away from owners. Thus, dominium is given a higher priority over imperium, and the right to rule by nations is constrained by international institutions. Capitalism is not left to self-regulate but needs oversight and active management to protect the dominium. Neoliberals believe there is a need to constrain democracy in a pure form that will subvert property rights in an effort to redistribute wealth. Neoliberals want an active legal framework to protect property rights and allow the freedom of capital to move and be controlled by owners.  

Sorkin's 1929 - A tale of personality

 

I finally got around to reading Andrew Ross Sorkin’s 1929: Inside the Greatest Crash in Wall Street History - and How it Shattered a Nation. His narrative style is compelling for those who do not want to read dry financial history. The characters come alive with his writing, but I did not come away with any new insights into the stock market crash. There were signs before the October crash, so it was not a total surprise. Excess leverage, margins that were too low, excess greed, and herd mentality, but we already knew that. While I liked reading about the characters, I kept asking why we didn’t hear more about the central bankers. What about some of the surviving brokers? How about some of the businessmen outside of Wall Street? 

Do I better understand the psychology of bubbles and the 1929 crash? I don't think so. Perhaps I am jaded by all my reading on the topic, but did I learn anything new beyond the fact that the same tropes of greed and leverage are always with us?

What does 1929 tell us about markets today? Not much. There is significant leverage, crowd behavior, misinformation on policy choices, and fear of taking action. Perhaps that is the message. Things don't change.

Words have uncertainty - The enemy of precision for investors

 

With the evolution of LLM and natural language processing, there is a closer connection between the discretionary and quantitative world, yet the two are not perfectly linked. There is uncertainty in both worlds. For the quant, there is model and parameter uncertainty. For the discretionary trader or non-quant, the problem is the precision in words. What you say may not be precise by you as the sender and by the receiver. 

We have discussed this issue of precision in language in the past, yet most investors still seem to be at risk from word uncertainty. Just think of all the Twitter words and Substack posts driven by language. Are these words given any quality control? If you look at the research, the answer is no. If you look at the range of meaning for these words of estimative probability, you will have to agree that there is ambiguity concerning the words often used by any decision-maker. Ask for specifics. Ask for the actual probabilities. Close the range of uncertainty.

See "Variability in the interpretation of probability phrases used in Dutch news articles — a risk for miscommunication."

Words of Estimative Probability (WEP) - Words matter and poor precision leads to decision failures

Imprecise language - The big problem with investment analysis

Language, perception, and numbers - The translation problem

Sherman Kent - the godfather of precision in forecasting language

Sherman Kent - My guy for precision in forecasting language

Sherman Kent - The analyst's analyst - Be precise with your forecasts

Sherman Kent and the problem between warner and warnee

Risk management is in the preparation

Don’t panic. Yes, it is time to start to panic. But what is panic? It is a forced action in response to the threat of uncertainty. An investor does not know what to do. There is no precise plan of action because the environment and market behavior are unclear and highly dynamic. Market actions, as reflected in prices, are unclear, and players' actions within the market cannot be determined. 

The only way to deal with a panic is through careful planning. But how can you plan for what may not have been anticipated? The only solution is to run scenarios or thought experiments on possible reasons for panic and then work through possible responses. This is not easy, and there is no reason you will get the drivers of panic right, but by conducting these exercises, you will identify common themes for addressing the unknown. 

Facts, information, and knowledge - Not all the same

 

There are no facts, only interpretations - Friedrich Nietzsche. 

What is a fact? A snippet of information. Something you did not know. A fact is unprocessed information. It does not have any context. Information is processed facts. There is some meaning or context given to the fact. Knowledge will be the applied understanding of that information or fact. Anyone can spout facts with no meaning but facts are usually used in an argument. Facts are used to persuade. Facts, when used as a tool of persuasion, need to be turned into information through knowledge.

Are facts reality? Yes. Facts do not have feelings. Yet knowing facts is not useful without processing and some knowledge; that is where most get into trouble. The disagreement is not with the facts but with the interpretation.

More on the Sharpe ratio - Look for its stability

 

A recent paper introduces a new concept to help investors assess managers and trading strategies: the Sharpe Stability Ratio (SSR). See “The Sharpe Stability Ratio:Temporal Consistency of Risk-Adjusted Performance”. This performance metric accounts for the temporal consistency of risk-adjusted returns. An investor, if given two Sharpe ratios with the same value, should choose the one that has more stable characteristics. You should like the persistent Sharpe ratio. This paper treats the Sharpe ratio as a rolling performance measure. It defines stability as the ratio of the mean rolling performance to the heteroskedasticity- and autocorrelation-consistent (HAC) standard deviation. 

Using the time-series approach can help analyze point-in-time SR or the probabilistic Sharpe ratio (PSR). Given strong serial correlation in the Sharpe ratio, arising from the rolling average and return consistency, the HAC correction provides a better measure than simply scaling by the standard deviation.

The important issue for investors is to look at persistence and consistency with strategies. This may be the true hallmark of skill.

Uncertainty about signals and price impact

Every model will have signal noise or uncertainty, and every model will have imprecise impact uncertainty from trading. This is a certainty because any training set will have to be imperfect. Hence, we should expect performance problems due to parameter uncertainty. Modelers should take this into account in their work. 

First, the model’s Sharpe ratio will be lower than expected from what is generated from the training set. There will be estimation error and model misspecification. Second, the model will affect transaction costs, with the impact being greater for smaller and less liquid stocks. Notably, weak signals will have less impact on trading costs, while strong signals will have a greater impact on trading costs. See “Trading with Uncertainty about signals and price impact”.

How do you solve these problems? One way to solve the problem is to define a reference model and then assess the costs associated with variations from it. The uncertainty can be managed to lock in a reasonable Sharpe around the reference level. The math in this paper is not easy, but the key is to be aware of the problem and to place bounds on what is possible.  

Beta is sensitive to the level of risk aversion

We have just written about the impact of changing beta. See There is no one beta - It changes across regimes. This is not new information, but researchers have taken a deeper look at the issue and have found some interesting relationships. Another paper that has found an interesting beta relationship is “Risk Appetite and (Mis)Pricing”. It has examined some beta portfolios conditional on high and low risk aversion. The risk aversion index was developed in prior research and is not new, but it has not been used in this type of study.

The results are strong and very thought-provoking. In a high-risk aversion environment, the researchers find a positive relationship between beta and returns. In contrast, in a low-risk aversion environment, there is a slight negative relationship between beta and returns. This can help explain why we do not find the usual CAPM relationship in the data. When risk aversion is high, the market risk premium idominatesother factors that may create distortions, such as sentiment. When risk aversion is low, mispricing becomes more important, and there is a positive relationship with a positive intercept. The study carefully examines the evidence and finds that risk aversion plays a key role in determining whether the CAPM holds or fails. When aversion to risk is low, sentiment-driven mispricing will be the key driver of returns and will offset the market risk premium effect.

 

"Look at your fish" - same with market prices

There is importance in looking closely at the things we study. There is an old parable from Samuel Scudder called "Look at your fish". The story can best be described in "The Student, the Fish, and Agassiz," a 19th-century educational parable in which Harvard professor Louis Agassiz forces a student to study a dead fish for days, using only observation and sketching, to teach that true knowledge comes from intense, firsthand examination. It emphasizes finding "general laws" through detail.

The same process can be applied to markets. We can start with price charts. Look at your charts. Look at the prices, but just don't look once; look deeply into what the markets may be saying. Then, after looking at the prices, look at the news surrounding the prices. This does not mean that everything has to have a pattern, but for any analysis, the first order of business is looking at the data. 

See before starting to analyze. 

There is no one beta - It changes across regimes

 

An interesting but simple paper, “Your Beta Is Wrong Regime-Dependent Alpha & Beta for Major Asset Classes”, explores the issue of regime-dependent beta. Your beta is not stationary, so alpha will not be stable but will move with the regime. This does not mean that you should calculate beta on a rolling basis; assume that beta is regime-dependent, and when the regime changes, so does the beta. Below are two examples of significant changes in beta. One shows silver, and the other is for Alphabet, one of the classic Mag 7 stocks. 

Do not assume there is one beta for any asset. This may seem obvious, but when seen in a distribution, the numbers are stark.

Think of global equity markets as a network

 We have been spending more time thinking about markets as networks or clusters. Don’t think about asset returns in isolation, but through the connections across markets and regions. Some of the latest work in this is presented in the paper, “Clustred Network Connectedness: A New Measurment Framework with Applicaitons to Global Eqiuty Markets” by Buchwalter, Diebold, and Tilmaz. 

These authors have been working on the network process for asset returns through variance decomposition of VAR models. From these models, the authors have been able to distinguish causality from and to markets across a wide set of markets. Their latest work on global equity markets seeks to address econometric issues arising from the decomposition method. This process of decomposition will provide a different narrative but will also answer questions about whether there is contagion or just co-movement across the network. The graph above shows the traditional method for forming the clustered identification. The graph below looks at the same data, accounting for groupings within the network after accounting for generalized identification.

Note that in the clustered identification, the US equity market serve as the center of netwrok behavior while the generalized idienificaiton which accoutns for correlation within groupinsg of the 16 equity markets studied, shows the high connection that is the focus of the EU cluster. Both provide interesting interpretations for how equity markets are connected. 

 

Good News - Bad News - overreaction to the bad news

There is good news and bad news that comes to the markets through new information that impacts expectations. News will have a differential impact, and investors should always be ready for it. Good news will drive prices higher, and of course, bad news will have the opposite effect, yet news will have a differential impact. Good news will usually be met with underreaction, while bad news, at the extreme, will be met with overreaction. To put it simply, the bad news forces investors to sell, and there has to be a buyer on the other side of the trade. To find the buyer, the markets will have to overreact to provide the buyer with a premium for considering the higher risk posed by the bad news. In the case of good news, there is no forced selling that requires new buyers. There will be a reaction, and there may be some extreme buying, but the buying excess is driven by a supply shortage, not by a need for a premium to induce buyers. 

Oil shocks and war - This could be different

UBS provides an interesting chart on the impact of war on oil prices. As expected, there will be a positive price shock, but it usually returns to normal after 4-5 months. Call this a fear factor. There will be some hoarding at the beginning of the war to protect inventories. Once the worst is over and the disruption is viewed as manageable, the price increase will be reversed. Yet, you cannot extrapolate from this evidence that the current situation will be normal. First, there is no reason to expect a return to normalcy. We only know that after the fact. Second, a disruption ot the Middle East is different from a war in other regions. If infrastructure is lost due to the destruction of refining capacity, there cannot be a quick adjustment. Oil can be pumped, but without refining, a "soft target" there will not be any easy way to create the end product needed by consumers. Capital expenditure for refining is costly and long-term, unlike the sinking of a tanker or the closing of a strait. The focus for any oil shock should be centered on what is happening to infrastructure.