Weekly Recap
Latest research on investing and trading
Welcome to this week’s roundup of the latest research on investing and other valuable resources. Below, you’ll find a curated list, with each title linking to its source for more details.
Thank you to everyone who shared feedback on the newsletter format. Responses were roughly split 50/50 between keeping the previous format and the new one I tested last week. For now, I’ll return to the previous format. I hope you find value in this week’s edition.
Crypto
Risk Premiums in the Cryptocurrency Market (Akbari and Ekponon)
Sorting cryptocurrencies on their betas with respect to stock market returns and the VIX generates a significant risk premium, suggesting that stock-market factors are priced in the cryptocurrency market.
Arbitrage Trading between Decentral and Central Cryptocurrency Exchanges (Schwertfeger and Vogt)
This paper develops a trading bot exploiting arbitrages between centralized and decentralized exchanges, generating profits in live trading.
Order Flow and Cryptocurrency Returns (Anastasopoulos et al.)
The authors find that signed volume data is a significant short-term predictor of cryptocurrency returns, generating profitable long-short strategies after transaction costs.
Equity
Decoding High-Volume Stock Momentum: Disagreement or Disposition? (Jin et al.)
The momentum effect observed in high-volume stocks is primarily driven by investor disagreement, suggesting one can possibly time momentum strategies using proxies for investor disagreement.
Digging into maxing out: A re-examination of MAX anomaly (Ince and Ozsoylev)
The authors propose improving the MAX strategy, which sorts stocks on their past max daily returns, by first controlling for stocks' market betas.
Market Risk Premium: Best Linear Predictor in High Dimension (Jiang et al.)
This paper proposes a linear predictive factor model that outperforms several competing models, including principal components, partial least squares, and several machine learning methods, in predicting returns on the S&P 500.
Quarterly Asset Growth, the Cross Section of Stock Returns, and Subjective Beliefs (Wang)
The author shows that decomposing firms’ quarterly asset growth into its components, such as cash growth and inventory growth, uncovers new sources of predictability. Moreover, the paper suggests a behavioral explanation for the investment growth anomaly in that investors become overly optimistic about the profitability of high investment growth firms, eventually leading to price corrections and low future returns.
Machine Learning and Large Language Models
AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors (Shi et al.)
This paper develops a two-step alpha mining methodology, where the first step generates alpha factors, and the second step times the factors based on their recent performance and forms a portfolio. Applied to Chinese stocks, the model outperforms a range of competing models.
A Deep Learning Approach for Trading Factor Residuals (Long and Xiao)
The authors replicate a statistical arbitrage strategy from a previous study, applying it to more recent data. Using Convolutional Neural Networks and transformers to analyze factor model residuals, the researchers find very high Sharpe ratios, although the results are before transaction costs.
Pixel to Profit (Nazemi)
This paper transforms cryptocurrency price data into color-coded images, which are then fed into a Convolutional Neural Network to forecast returns, finding improved predictability over traditional methods.
Ranking factors with news (Li et al.)
Certain annually updated firm characteristics in asset pricing models can be substituted with monthly firm-specific news articles, improving predictive accuracy and Sharpe ratios.
International Corporate Bond Returns: Uncovering Predictability Using Machine Learning (Li et al.)
The authors predict returns on international corporate bonds using a range of machine learning models and find significant predictability, with features related to downside risk and illiquidity being most influential outside the U.S.
A machine learning ensemble approach to predict financial markets manipulation (Franus et al.)
Using an ensemble of machine learning models, this paper proposes a real-time measure of suspected spoofing and validates its effectiveness using a unique dataset from the Moscow Stock Exchange.
Taming the Global Factor Zoo (Chen et al.)
Starting with 152 anomalies across 36 countries, the authors estimate a global factor model consisting of 6 factors that prices the cross-section of global stock returns better than competing models. Interestingly, their global factor model outperforms local factor models.
Options
Intraday Option Return: A Tale of Two Momentum (Da et al.)
Prior research has found seasonal patterns in intraday stock returns where for example returns today between 3:30 pm and 4 pm predict returns tomorrow during the same interval. This paper finds a similar pattern for delta-neutral straddle returns.
Option-Implied Crash Index (Gao and Pan)
The authors obtain estimated crash risk from S&P 500 out-of-the money options and construct a crash index. The crash index is uncorrelated with the VIX and has steadily increased since the Great Financial Crisis.
Volatility
Do Retail Structured Products Distort Equity Volatilities? (Barthe)
This paper shows how the issuance of structured products on equities compresses the volatility of the underlying due to the issuers' delta hedging. Going long volatility on stocks with high structured product volumes and short those with low volumes is profitable, even accounting for trading costs.
Blogs
From the Pits to the Page: A Conversation with Kris Abdelmessih (Robot Wealth)
Fast trend following (Quantitativo)
NLX Finance’s Hybrid Asset Allocation 60/40 (Allocate Smartly)
GitHub
Medium
Uncertainty Quantification in Time Series Forecasting (Dancker)
Predict Price Movements: Image Recognition for Smarter Stock Predictions (Ingle)
Podcasts
PJ Sutherland - The Complementary Dynamics of Mean Reversion and Trend-Following Strategies (The Algorithmic Advantage)
Volatility and Trends: What 2024 Held for Trend Followers ft. Katy Kaminski (Top Traders Unplugged)
Episode 335 - "What About Warren Buffett?" (Rational Reminder)
Interview with Marsten Parker (Line Your Own Pockets)
Ep. 1317: Tom Basso Interview with Michael Covel on Trend Following Radio (Michael Covel)
Dispelling Big Investing Myths | Dan Rasmussen (Excess Returns)
Last Week’s Most Popular Links
Formula Investing (Hanauer and Schwartz)
Lead-Lag Relationships in Market Microstructure (Schmidt et al.)
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.