Analyzing Option Chain Bid–Ask Spreads with Machine Learning

This paper investigates the determinants of option bid–ask spreads using machine learning techniques. We analyze a cross-sectional dataset of Apple Inc. (AAPL) call options, focusing on the relative bid–ask spread as the target variable. By comparing linear models with ensemble methods such as Random Forests and XGBoost, we find that nonlinear machine learning methods significantly outperform traditional OLS regression. The most influential factors are moneyness, implied volatility, and time to expiration, while volume and open interest have limited predictive power. Results suggest that spreads are driven by a mix of market microstructure dynamics, capital constraints, and regulatory requirements such as FINRA Rule 4210. Our findings highlight the value of ML in financial microstructure modeling and offer insights relevant to traders, regulators, and liquidity providers.