Perspectives on Risk - August 29, 2022
Portfolio Optimization; For My Former-NY-Fed Homies; Random Lessons-Learned; Steve Bannon Is Not Entirely Wrong; Better Bar Charts
Summers almost over. Time to clear out my backlog and maybe give you a few things to read over the upcoming long weekend.
Portfolio Optimization
A consensus has recently emerged that many variables in addition to the level, slope, and curvature of the yield curve can help predict bond returns. The statistical tests that led to this conclusion are subject to previously unrecognized size distortions arising from highly persistent regressors and lagged dependent variables. We revisit the evidence using tests that are robust to this problem and conclude that the current consensus is wrong. Only the level and the slope of the yield curve are robust predictors of bond returns, and there is no convincing evidence of unspanned macro risk.
Missing data is a prevalent, yet often ignored, feature of company fundamentals. In this paper, we document the structure of missing financial data and show how to systematically deal with it. In a comprehensive empirical study we establish four key stylized facts. First, the issue of missing financial data is profound: it affects over 70% of firms that represent about half of the total market cap. Second, the problem becomes particularly severe when requiring multiple characteristics to be present. Third, firm fundamentals are not missing-at-random, invalidating traditional ad-hoc approaches to data imputation and sample selection. Fourth, stock returns themselves depend on missingness.
Optimal Versus Naive Diversification: How Inefficient is the 1/N Portfolio Strategy?4
We evaluate the out-of-sample performance of the sample-based mean-variance model, and its extensions designed to reduce estimation error, relative to the naive 1/N portfolio. Of the 14 models we evaluate across seven empirical datasets, none is consistently better than the 1/N rule in terms of Sharpe ratio, certainty-equivalent return, or turnover, which indicates that, out of sample, the gain from optimal diversification is more than offset by estimation error. Based on parameters calibrated to the US equity market, our analytical results and simulations show that the estimation window needed for the sample-based mean-variance strategy and its extensions to outperform the 1/N benchmark is around 3000 months for a portfolio with 25 assets and about 6000 months for a portfolio with 50 assets. This suggests that there are still many “miles to go” before the gains promised by optimal portfolio choice can actually be realized out of sample.
I was drawn to this paper by an observation by Danny Kahneman in his latest book Noise. He has an observation that ’frugal’ or simple models quite often outperform more complex models due to data and parameterization issues. Has anyone tried to put learnings from Noise into practice? I’d be interested if you have.
Credit Factor Investing with Machine Learning Techniques5
The most common models to assess asset returns are a linear combination of risk factors. We have employed tree-based machine learning algorithms to capture nonlinearities and detect interaction effects among risk factors in the EUR and USD credit space. We have built a nonlinear credit pricing model and compared it to our baseline linear credit pricing model using error metrics on training and testing sets and during different periods. In sample error metrics revealed the benefit of tree-based regressions. Then, we analysed the explanatory and predictive power measure by factor category and by period in order to evaluate the contribution of each factor in the explanation and prediction of credit excess returns. We found value in adding alternative factors to a traditional factor model and point out which of them prevail across different time horizons and during market crisis periods. Finally, tree-based regressions methods assisted us in improving our understanding of prices through the interaction between features and between each feature and the output of the model.
For My Former-NY-Fed Homies
The NY Fed vs Larry Summers6 highlights this Liberty Street blog post, How Much Did Supply Constraints Boost U.S. Inflation?, about a paper titled Challenges for monetary policy in a rapidly changing world7
The current debate on whether the Federal Reserve can engineer a soft landing needs to disentangle the drivers of U.S. inflation. Our work shows that inflation in the U.S. would have been 6 percent instead of 9 percent at the end of 2021 without supply bottlenecks. Our quantitative results clarify why some pundits were wrong to predict a transitory surge in inflation, while others were right in predicting high inflation, but for the wrong reasons. Put differently, fiscal stimulus and other aggregate demand factors would not have driven inflation this high without the pandemic-related supply constraints. In the absence of any new energy or other shock, it is therefore possible that the ongoing easing of supply bottlenecks will cause a substantial drop in inflation in the near term.
The links are the key. Love me some passive aggressive economist smack.
I, of course, lol’d because the Fed clearly made them add this to the Alphaville post:
Update: As the generic disclaimer on the Fed’s Liberty Street Economics blog says, “the views expressed in this post are those of the author(s) and do not necessarily reflect the position of the Federal Reserve Bank of New York or the Federal Reserve System. Any errors or omissions are the responsibility of the author(s)”.
Random Lessons-Learned
They Quit Goldman’s Star Trading Team, Then the Bank Raised Alarms8 (Bloomberg)
Goldman fired the pair — Jon “JP” Paul and Sina Lashgari — from jobs on its program-trading desk, telling regulators they accessed sensitive computer code without authorization or a valid business purpose. Goldman suspected, but couldn’t prove, they intended to swipe some of the secret sauce behind several hundred million dollars in revenue, according to documents seen by Bloomberg.
A third-party forensic firm that both sides agreed to hire rooted through their computers and mobile phones. The review didn't find evidence of data transfer or any communication “that would suggest an intention to initiate mass deletions or transfers,” according to an April 4 report seen by Bloomberg.
Goldman sought a broader review of their communications, couldn’t make much headway and weeks later fired the two vice presidents. It then levied an unusual accusation in a database maintained by the Financial Industry Regulatory Authority that they improperly accessed systems and that Lashgari took steps to cover his tracks.
The managerial contradictions of extroverted financialization: the rise and fall of Deutsche Bank9
This paper traces Deutsche’s rise and fall from the 1980s onwards, and argues that this dual development is integrally linked to a process of extroverted financialization (EF). EF characterized Deutsche’s attempts to respond to US-led financialization by routing itself into US money markets.
The key was that Deutsche’s Board could not adapt to the changes in market structure and the increase in non-bank market participation. My only quibble is that, like most other papers on DB, it ignores the affect of the unfortunate and tragic death of Edson Mitchell on DB’s plans.
How to Lose Money in Derivatives: Examples from Hedge Funds and Bank Trading Departments10
What makes futures hedge funds fail? The common ingredient is over betting and not being diversified in some bad scenarios that can lead to disaster. Once troubles arise, it is difficult to take the necessary actions that eliminate the problem. Moreover, many hedge fund operators tend not to make decisions to minimize losses but rather tend to bet more doubling up hoping to exit the problem with a profit. Incentives, including large fees on gains and minimal penalties for losses, push managers into such risky and reckless behavior. We discuss some specific ways losses occur. To illustrate, we discuss the specific cases of Long Term Capital Management, Niederhoffer’s hedge fund, Amaranth and Société Genéralé. In some cases, the failures lead to contagion in other hedge funds and financial institutions. We also list other hedge fund and bank trading failures with brief comments on them.
The Origins and Growth of the Family Office11
Today, thousands of family offices collectively invest an estimated $6 trillion in assets. With flexible long-term capital they can be active across markets and asset classes, becoming key investors particularly for smaller investment managers and deals. And yet most of them remain practically invisible.
The birth of the modern family office happened almost by accident. Its success led to a windfall profit in one of the early 20th century’s most notable mergers.
Steve Bannon Is Not Entirely Wrong
Bucco Capital recirculated these quotes from a 2019 NY Magazine interview with Steve Bannon. Having played a small part in all this, it does hit home, particularly when the justification for the bailouts was to prevent the contagion from reaching ‘main street.’
Better Bar Charts
Ethan Mollick asked Midjourney (AI software akin to Dalle-e) to create bar charts in various styles. The full set can be found at this tweet stream. Here are a few of my favorites. Never settle for Powerpoint or Excel again.
More Stuff
Did you know…NASA has a Space Weather Prediction Center?
Amsterdam: 1971 vs 2020. Same street. Change is possible. Which do you prefer?
Bauer, Hamilton, Robust Bond Risk Premia, FRB San Francisco
Cochrane, Comments on “Robust Bond Risk Premia” by Michael Bauer and Jim Hamilton, FRB San Francisco
Bryzgalova, Lerner, Lettau, Pelger, Missing Financial Data
DeMiguel, Garlappi, Uppal, Optimal Versus Naive Diversification: How Inefficient is the 1/N Portfolio Strategy?
Cherief, Ben Slimane, Dumas, Fredj, Credit Factor Investing with Machine Learning Techniques
The NY Fed vs Larry Summers, FT Alphaville
Giovanni, Silva, Yıldırım, Challenges for monetary policy in a rapidly changing world, ECB Forum on Central Banking
Natarajan, Abelson, They Quit Goldman’s Star Trading Team, Then the Bank Raised Alarms, Bloomberg
Mareike Beck, The managerial contradictions of extroverted financialization: the rise and fall of Deutsche Bank, Socio-Economic Review
Llieo, Zimba, How to Lose Money in Derivatives: Examples from Hedge Funds and Bank Trading Departments
Gieschen, The Origins and Growth of the Family Office, Net Interest