Option return predictability with machine learning and big data

Arbeitspapier

Drawing upon more than 12 million observations over the period from 1996 to 2020, we find that allowing for nonlinearities significantly increases the out-of-sample performance of option and stock characteristics in predicting future option returns. Besides statistical significance, the nonlinear machine learning models generate economically sizeable profits in the long-short portfolios of equity options even after accounting for transaction costs. Although option-based characteristics are the most important standalone predictors, stock-based measures offer substantial incremental predictive power when considered alongside option-based characteristics. Finally, we provide compelling evidence that option return predictability is driven by informational frictions, costly arbitrage, and option mispricing.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: CFR Working Paper ; No. 21-08

Classification and Topics

• Classification: Wirtschaft ; General Financial Markets: General (includes Measurement and Data) ; Asset Pricing; Trading Volume; Bond Interest Rates ; Contingent Pricing; Futures Pricing; option pricing ; Information and Market Efficiency; Event Studies; Insider Trading
• Subject: Machine learning ; big data ; option return predictability

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Bali, Turan G. ; Beckmeyer, Heiner ; Moerke, Mathis ; Weigert, Florian
• Event: Veröffentlichung
• (who): University of Cologne, Centre for Financial Research (CFR)
• (where): Cologne
• (when): 2021

Further information

• Handle: http://hdl.handle.net/10419/242849
• Last update: 10.03.2025, 11:45 AM CET