The Joint Cross Section of Option and Stock Returns Predictability with Big Data and Machine Learning

67 Pages Posted:

See all articles by Ruslan Goyenko

Ruslan Goyenko

McGill University - Desautels Faculty of Management

Chengyu Zhang

McGill University - Desautels Faculty of Management

Date Written: December 11, 2020

Abstract

Using large set of stock and option specific characteristics, and machine learning, we first provide a comprehensive analysis of what drives expected delta hedged and delta-neutral straddle returns of equity options. In contrast to the previous literature, we find that option, rather than stock, characteristics are more important predictors of option returns. Second, option, rather than stock, characteristics are more important predictors of stock returns. In terms of variable importance for stock return predictability, most of machine learning methods we use outweigh option illiquidity. Consequently, stock long-short portfolio strategies formed conditioning on option illiquidity outperform in out-of-sample those of machine learning portfolios, which in turn outperform the market. The results point to positive option illiquidity premium in stock returns, as well as to overall competitive advantage of option market characteristics in identifying mispricing opportunities in the stock market.

Keywords: Machine learning, Option pricing, Stock return predictability

JEL Classification: G10, G12, G13, G14

Suggested Citation

Goyenko, Ruslan and Zhang, Chengyu, The Joint Cross Section of Option and Stock Returns Predictability with Big Data and Machine Learning (December 11, 2020). Available at SSRN: https://ssrn.com/abstract=

Ruslan Goyenko (Contact Author)

McGill University - Desautels Faculty of Management ( email )

1001 Sherbrooke St. West
Montreal, Quebec H3A1G5 H3A 2M1
Canada

Chengyu Zhang

McGill University - Desautels Faculty of Management ( email )

1001 Sherbrooke St. West
Montreal, Quebec H3A1G5 H3A 2M1
Canada

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
23
Abstract Views
54
PlumX Metrics