End-to-End Deep Learning for Equity Options Trading

Summary

The document describes an end-to-end machine learning approach that maps options market data directly to trading signals. Unlike approaches that specify market dynamics or rely on an option pricing model, it trains models to learn the relationship between observed data and trading decisions. It also incorporates turnover regularization to account for trading activity and its costs.

The reported backtest spans more than a decade of equity options on S&P 100 constituents. The authors report better risk-adjusted performance than rules-based strategies and further gains from turnover regularization under very high transaction costs. The summary does not provide model details, performance figures, or information about validation design, so the strength and practical generality of the results cannot be assessed from this description alone.

Key ideas

• The approach learns trading signals directly from options market data without specifying market dynamics or an option pricing model.
• It uses an end-to-end deep learning model to map observations to trading decisions.
• Turnover regularization is included to address trading activity and transaction costs.
• The reported backtest covers more than a decade of options on S&P 100 equities.
• The authors report improved risk-adjusted performance over rules-based strategies.

Tags

# Deep Learning for Options Trading: An End-To-End Approach


# Deep Learning for Options Trading: An End-To-End Approach









We introduce a novel approach to options trading strategies using a highly scalable and data-driven machine learning algorithm. In contrast to traditional approaches that often require specifications of underlying market dynamics or assumptions on an option pricing model, our models depart fundamentally from the need for these prerequisites, directly learning non-trivial mappings from market data to optimal trading signals. Backtesting on more than a decade of option contracts for equities listed on the S&P 100, we demonstrate that deep learning models trained according to our end-to-end approach exhibit significant improvements in risk-adjusted performance over existing rules-based trading strategies. We find that incorporating turnover regularization into the models leads to further performance enhancements at prohibitively high levels of transaction costs.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.