Microstructure in the Machine Age: Frictions Still Matter
This paper shows that classic market microstructure measures like VPIN, Amihud, and Roll still have predictive power—even in modern, high-frequency, machine-traded markets.
ML & AI
Data-driven trading using machine learning, deep learning, and AI-enhanced models.
Latest posts — page 3
Two Million Strategies Later: How p-Hacking Distorts Financial Research
This paper runs over 2 million trading strategies using CRSP and Compustat data to expose how widespread p-hacking is in finance. After accounting for multiple testing and requiring economic significance, fewer than 20 strategies remain—and none have theoretical justification.
Predicting Returns with Machine-Learned News Sentiment
This paper develops a machine learning method that builds its own sentiment dictionary from scratch to predict stock returns from news articles. The resulting strategy delivers much higher Sharpe ratios than those based on commercial scores like RavenPack or dictionary-based methods.
Reimagining Price Trends with AI
Sharpe ratio up to 7.2. A powerful AI-driven approach to price trends, demonstrating that machine learning can outperform traditional technical indicators.
Investor Inattention and Market Anomalies: How Media Coverage Drives Mispricing
Taking advantage of limited attention in anomaly trading: The average Sharpe ratio documented in the paper is 1.09 (min: 0.62 ROE, max: 4.45 MOM). Top anomalies: MOM (4.45), ROA (2.40), PEAD (1.60), PERF (1.68)—all stronger in low media coverage stocks.
ChronoBERT: Eliminating Lookahead Bias in Financial Text-Based Strategies
Sharpe Ratio (H-L Portfolio): 4.80