Weekly Research Recap
Latest research on investing and trading
Here’s a fresh round of great investing research from the past week. Each paper below is carefully selected and includes a direct link to the original source for easy access.
Appreciate your continued support! If you’re finding value in these posts, feel free to like and subscribe if you haven’t already.
Asset Allocation
How Much Should You Pay for Alpha? Measuring the Value of Active Management with Utility Calculations (Ang and Basu)
Many investors chase high-performing funds expecting them to beat the market, but rarely ask how much that outperformance is actually worth to them. Even when a fund delivers strong returns, the benefit to investors shrinks once risk, fees, and overlap with a standard 60/40 stock-bond portfolio are considered. On average, investors should be willing to pay only about 19 basis points for equity funds and 10 for bond funds, since most funds add little uncorrelated return to an already well-diversified portfolio.
What is Total Portfolio Approach? A Practitioner Summary (Elkamhi and Lee)
This paper discusses an alternative framework to Strategic Asset Allocation (SAA) called the Total Portfolio Approach (TPA). TPA addresses SAA’s shortcomings, such as the difficulty of rebalancing illiquid assets, the failure of historical correlations during crises, and the inability to adapt to shifting macro regimes. It introduces several solutions, including dynamic portfolio weights and scenario analysis to guide investment decisions.
Global Fund Managers' Beliefs, Perceived Mispricing, and Asset Allocation (Bastianello and Peng)
Many investors believe institutional managers have better insights than retail traders, but we rarely see direct evidence of their thinking. This paper changes that by analyzing 30 years of data from the Bank of America Global Fund Manager Survey. It finds that when these managers see the market as undervalued, future long-term returns tend to be higher. Their beliefs are tied to future portfolio shifts and mutual fund flows, and they often take a contrarian stance in direct contrast to retail investors.
Commodities
Short-Term Basis Reversal (Rossi, Zhang, and Zhu)
Many trading strategies focus on individual futures contracts or long-term trends, but short-term return spreads between nearby futures have received less attention in academic research. This paper shows that the weekly return difference between front- and second-month commodity contracts tends to reverse. Both cross-sectional and time-series strategies exploiting this pattern are profitable, with pre-cost Sharpe ratios above one. The effect is stronger when volatility is high and maturities incorporate news at different speeds. Similar patterns also appear in stock index futures and bonds.
Equities
The short-duration premium and news announcements (Beckmeyer and Meyerhof)
In the data, the term structure of expected equity returns is downward sloping: Short-duration stocks tend to outperform long-duration ones. This paper estimates the short-duration premium at around 3.7% annually, but finds it to be 16 times larger on earnings announcement days. Since long-duration stocks are often overvalued due to overly optimistic expectations, their prices tend to correct on earnings days, leading to sharp underperformance relative to short-duration stocks.
Trump Tariffs and Stock Prices (Yilmazkuday)
Many investors worry about how protectionist trade policies and related uncertainty affect markets. This paper shows that U.S. stock prices initially rise when tariffs are imposed, but fall over time as the longer-term costs become clear. Trade policy uncertainty, while not hurting stocks right away, also leads to lower prices in the long run. Together, these forces explain a large portion of market volatility.
Factor Investing
Caveats of Simple Factor Timing Strategies (Blitz)
Many investors try to boost returns by shifting between factors like value, momentum, or size. This paper reviews several such strategies, including short-term momentum, seasonal timing, volatility scaling, and sentiment-based allocation, and finds that while they may show strong historical returns, many suffer from performance decay, high trading costs, or rely heavily on known effects like standard momentum. As a result, investors should be cautious about whether factor timing truly adds value.
The Multifactor Risk-Return Tradeoff (Baba Yara, Boons, and Frehen)
Several factor models, such as the Fama-French five-factor model, aim to explain expected returns through exposure to common risk factors. This paper shows that it's not just the volatility of individual factors that matters, but how these factors move together. Covariances between factors explain a much larger share of return variation than variances alone. As a result, investors should focus on the interplay among factor risks, not just their standalone volatility.
Factor Investing Lecture 1: Intro to Factor Investing (Shi)
These lecture notes provide an introduction to factor investing, covering areas such as the evolution of asset pricing models, the construction and interpretation of factor models, and the practical implementation of factor-based strategies.
Factor Investing Lecture 5: Multiple Hypothesis Testing (Shi)
These notes provide a clear overview of the challenges in empirical factor research, especially the risk of false discoveries when testing many strategies, covering both frequentist and Bayesian methods to adjust for multiple hypothesis testing.
Hedge Funds
Financial Intermediary Risk and the Cross-section of Hedge-fund Returns (Dahlquist, Rottke, Sokolovski, and Sverdrup)
Hedge fund performance varies widely, and it's often hard to explain why some funds outperform. This paper finds that part of the answer lies in how sensitive hedge funds are to shocks in the financial health of major Wall Street dealers. Funds with higher exposure to these shocks outperform low-exposure funds by around 7% annually. These returns appear to compensate for bearing systematic risk that delivers long-run rewards but leads to losses during financial stress.
Machine Learning and Large Language Models
Stock portfolio selection based on risk appetite: Evidence from ChatGPT (Schneider and Yilmaz)
Retail investors often struggle to build portfolios that match their risk appetite. This study finds that ChatGPT can construct stock portfolios tailored to different risk levels by adjusting sector exposure, favoring defensive industries for cautious investors and volatile growth sectors for those seeking higher returns. Some models even outperform the market, especially in the U.S., but outcomes depend on the version used.
Forecasting Intraday Volume in Equity Markets with Machine Learning (Cucuringu, Li, and Zhang)
Forecasting intraday trading volume is essential for executing large trades efficiently. Using data on S&P 500 constituents, this paper shows that machine learning, especially neural networks trained across many stocks, can significantly improve volume predictions. These enhanced forecasts help reduce transaction costs and improve trade execution through better VWAP strategies.
Introduction to Machine Learning (Younes)
This book introduces the mathematical tools that power modern machine learning, covering everything from optimization techniques and regression models to neural networks and generative modeling.
Between the Lines: Textual Features in Financial Reports and Expected Stock Returns (Cakici, Tang, and Zaremba)
Many believe that analyzing the tone or clarity of financial reports can reveal hidden trading signals. But when tested rigorously using 40 standard text-based features, such as sentiment, readability, and similarity, derived from a bag-of-words approach, these signals mostly fall flat. Any predictive power is confined to illiquid micro-cap stocks and fades over time. Investors looking for an edge are better off relying on traditional financial metrics or exploring more advanced language models beyond simple word counts.
TradExpert: Revolutionizing Trading with Mixture of Expert LLMs (Ding, Shi, Guo, and Liu)
This paper introduces TradExpert, an AI system that blends insights from news, price patterns, technical indicators, and company fundamentals using a team of specialized language models. Each day, it ranks stocks based on this combined view and simulates a buy-and-hold strategy on the top picks. The strategy is tested on DOW 30 stocks and delivers very high Sharpe ratios, although all performance metrics are reported before accounting for transaction costs.
FinTwit and LinkedIn
A Poor Person’s Transformer (Ernest Chan)
Profitability Retrospective: Key Takeaways for Investors (Wes Gray - Alpha Architect)
Introducing the FT's 'macro mood' index (Joel Suss - FT)
Intangible Assets (Kai Wu)
The impact of government debt on economic growth (Research Affiliates)
GitHub
Finance Toolkit - Financial ratios and indicators across asset classes
Public APIs - An extensive list of free APIs
Medium
Self-Tuning Trading Signals with K-Means and SuperTrend (Velasquez)
12 Python Libraries for Free Market Data That Changed How I Work (Algo Insights)
Separate Volatility Noise from Signal (Velasquez)
Podcasts
Peter Brandt: Unlocking Market Wisdom with a Trading Legend – Part 1 (AlphaMind)
Brett Steenbarger - Mental Keys to Quantitative Trading Success (The Algorithmic Advantage)
The Quiet Cost of Overfitting ft. Andrew Beer (Top Traders Unplugged)
Factor-based Investing with John Montgomery (Masters in Business)
Swing Trading Strategies Of The Pros (1-Hour Masterclass) (Desire To Trade)
Last Week’s Most Popular Links
The Intersection of Expected Returns (Sobotka)
Market-Dependent Momentum and Institutional Ownership (Wu)
Robust Optimization of Strategic and Tactical Asset Allocation for Multi-Asset Portfolios (Sepp, Ossa, and Kastenholz)
Disclaimer: This newsletter is for informational and educational purposes only and should not be construed as investment advice. The author does not endorse or recommend any specific securities or investments. While information is gathered from sources believed to be reliable, there is no guarantee of its accuracy, completeness, or correctness.
This content does not constitute personalized financial, legal, or investment advice and may not be suitable for your individual circumstances. Investing carries risks, and past performance does not guarantee future results. The author and affiliates may hold positions in securities discussed, and these holdings may change at any time without prior notification.
The author is not affiliated with, sponsored by, or endorsed by any of the companies, organizations, or entities mentioned in this newsletter. Any references to specific companies or entities are for informational purposes only.
The brief summaries and descriptions of research papers and articles provided in this newsletter should not be considered definitive or comprehensive representations of the original works. Readers are encouraged to refer to the original sources for complete and authoritative information.
This newsletter may contain links to external websites and resources. The inclusion of these links does not imply endorsement of the content, products, services, or views expressed on these third-party sites. The author is not responsible for the accuracy, legality, or content of external sites or for that of any subsequent links. Users access these links at their own risk.
The author assumes no liability for losses or damages arising from the use of this content. By accessing, reading, or using this newsletter, you acknowledge and agree to the terms outlined in this disclaimer.