Welcome to this week's roundup of the latest investing research! Below is a carefully curated selection of highlights, with each title linking directly to its source for further reading.
Thank you for reading and don’t forget to hit the like button!
Commodities
A Decomposition of the Cross-Section of Commodity Returns (Han, Dam, and Scholtens)
The paper breaks down commodity returns into price changes and yields, finding that speculation outweighs hedging as a key return driver. Financialization has strengthened the impact of broad market risks while reducing the influence of commodity-specific risks.
Crypto
The authors examine whether optimized diversification methods outperform a simple equal-weighted strategy in cryptocurrency markets. It finds that while predicting returns is challenging, forecasting volatility improves risk management. Simpler methods often outperform advanced models like deep learning due to lower variability and reduced transaction costs.
The $TRUMP Meme Coin: A Cryptocurrency Revolution or a Political Gimmick? (Krause)
The Trump coin was launched on Jan 18 2025 and quickly touched a market cap of $15 billion on the 19th before dropping by about 50% and stabilizing at around $6 billion. This paper studies its rapid rise, exploring how it combines financial speculation with public sentiment. It highlights the allure and risks of meme coins and discusses their impact on the future of finance.
Pricing Bitcoin and Other Assets with Conditional Optimization (Aldridge and Zhang)
The authors explore how changes in trading volume predict asset prices, with a primary focus on Bitcoin, and improve portfolio strategies across various asset classes. It introduces a method using volume changes to forecast returns, finding that Bitcoin and cryptocurrencies exhibit a nonlinear relationship, while traditional assets like equities show a more linear one.
Equities
Election Arbitrage During the 2024 U.S. Presidential Election (Jain, Ezhov, Liang, Liu, Wang, Zhou, Stoikov, and Cetin)
The study explores how financial markets react to U.S. presidential elections by creating two stock portfolios aligned with the policies of Trump and Harris, guided by shifts in prediction market odds. These portfolios target sectors benefiting from each candidate's policies and outperform benchmarks.
Machine Learning and Large Language Models
Developing Cryptocurrency Trading Strategy Based on Autoencoder-CNN-GANs Algorithms (Hu, Yu, Zhang, Zheng, Liu, and Zhou)
A new method for predicting cryptocurrency price movements and developing trading strategies is introduced. By combining several machine learning models, it filters noisy data, extracts patterns, and forecasts the direction of price changes. Testing on Bitcoin, the model demonstrates notable accuracy and profitability.
Can Chatgpt Outsmart the Market? (Erdem)
Can ChatGPT-4o create actionable and profitable stock portfolios? This paper tests its capabilities by analyzing portfolios it generated over six months. While the portfolios beat the S&P 500 in total returns, their ability to consistently achieve better risk-adjusted performance is unclear, as the alphas were statistically insignificant.
Market Microstructure
Anonymity, Signaling, and Collusion in Limit Order Books (Cartea, Chang, and Graumans)
The paper explores how market makers use large order sizes to signal their identity to each other. This signaling breaks the anonymity of trading, enabling market makers to avoid trading against each other and target smaller, retail orders for profit. The behavior aligns with a model of collusion, where market makers cooperate to maximize shared gains, widening spreads and increasing costs for other traders.
Mutual Funds
Rise and Fall: Post-Award Performance of Superstar Mutual Fund Managers (Gao, Sun, Wang, and Yan)
Award-winning mutual fund managers in China, celebrated for their “superstar” status, tend to attract more investments and launch additional funds post-recognition. However, they shift toward conservative strategies, engage in job-hopping or performance window dressing, and their funds underperform non-awarded peers, harming investors’ returns over time.
Options
A statistical technique for cleaning option price data (Visagie)
A method for cleaning errors in option price datasets is introduced, ensuring a more reliable analysis. It identifies and removes unrealistic prices, outliers, and duplicates, using statistical techniques without relying on specific pricing models. The cleaned datasets are shared publicly to support further research.
Portfolio Optimization
The study explores a method for improving investment portfolios by grouping stocks with K-Means clustering and optimizing each group to maximize risk-adjusted returns. The best portfolio significantly outperforms a standard equal-weighted approach.
"Double Descent" in Portfolio Optimization: Dance between Theoretical Sharpe Ratio and Estimation Accuracy (Lu, Yang, and Zhang)
How does increasing the number of assets in the mean-variance portfolio optimization framework affect performance? Initially, adding assets improves outcomes, but performance eventually declines due to overfitting. Surprisingly, the paper finds that beyond a certain threshold, performance improves again, similar to patterns in machine learning. This underscores the interplay of risk, complexity, and estimation precision.
Volatility
On the performance of volatility-managed equity factors — International and further evidence (Schwarz)
The paper studies how volatility targeting, adjusting portfolio exposure based on total or downside volatility, affects performance across 45 global stock markets. It finds that this approach benefits momentum and market-based strategies the most, but transaction costs often diminish gains. The performance of volatility targeting is higher in countries with slower trading.
Blogs
Interest Rates and Sector Rotation: Timing Sector ETFs With Interest Rates (QuantSeeker)
Iterative PSD Shrinkage (CSSA)
Private credit expansion (Macrosynergy)
GitHub
skfolio - Python library for portfolio optimization
talipp - Incremental Technical Analysis Library
Medium
Comprehensive Guide to Volatility Models (Filip)
Python + AI: Revolutionizing Algorithmic Trading with Qlib (DataScience Nexus)
19 Insanely Useful Python Automation Scripts I Use Every Day (Purrfect Software Limited)
Podcasts
032 - Dr Ernest Chan - The Breakthrough Uses of Machine Learning in Risk Management (The Algorithmic Advantage)
Busting 50 Years of Investing Myths | Rob Arnott (Excess Returns)
Market Turbulence: How to Adapt to Regime Changes in Investing ft. Alan Dunne & Mark Rzepczynski (Top Traders Unplugged)
How Oaktree's Howard Marks Spots a Market Bubble (Odd Lots)
Last Week’s Most Popular Links
Conditional short-term trend signals (Macrosynergy)
Intra-day Seasonality and Abnormal Returns in the Brent Crude Oil Futures Market (Ewald, Haugom, Ouyang, Smith-Meyer, and Stordal)
Creating & Backtesting 16 Popular Algo-Trading Strategies with Backtrader (Alexzap)
Disclaimer: This newsletter is for informational and educational purposes only and should not be construed as investment advice. The author does not endorse any specific securities or investments mentioned. While information is gathered from sources believed to be reliable, there is no guarantee of its accuracy, completeness, or correctness.
This content does not offer 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 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 are the author's own interpretations of the findings and content. These summaries should not be considered as definitive or comprehensive representations of the original works. Readers are encouraged to refer to the original sources for complete and authoritative information.
This newsletter contains 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 these external sites or for that of subsequent links. Users click on these links at their own risk.