Paper: arXiv 2407.21791

Authors: Wee Ling Tan, Stephen Roberts, Stefan Zohren

Abstract

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.

Complexity vs Empirical Score

  • Math Complexity: 8.0/10
  • Empirical Rigor: 8.5/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced neural network architectures with end-to-end optimization and regularization techniques, indicating high mathematical complexity. It demonstrates strong empirical rigor through backtesting on a decade of S&P 100 options data, rigorous data filtering, and evaluation against rules-based strategies.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Develop End-to-End DL Model for Options Trading"] --> B["Data Input<br>S&P 100 Equity Options >10 Years"]
  B --> C["Methodology<br>Deep Learning vs. Traditional Models"]
  C --> D["Computational Process<br>Training with Turnover Regularization"]
  D --> E["Backtesting<br>Risk-Adjusted Performance Evaluation"]
  E --> F["Key Findings<br>Improved Performance Over Rules-Based Strategies"]
  F --> G["Outcome<br>Robust Signals with High Transaction Costs"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes an end‑to‑end deep learning framework for options trading that learns mappings from market data to optimal trading signals without requiring option pricing models.

Source sentence
We introduce a novel approach to options trading strategies using a highly scalable and data-driven machine learning algorithm.

Assumes 4

  • Only standard monthly option contracts that expire on the third Friday of the month are used, with special settlements excluded. data
    Source sentence
    We consider only standard monthly option contracts that expire on the third Friday of the month and exclude any special settlements due…
  • Delta hedging is performed at initiation and the early‑exercise premium of American‑style options is ignored. execution
    Source sentence
    we disregard the early exercise premium embedded in the American-style options and therefore ignore the possibility of early assignment of short options.
  • A constant annualized volatility target of 15% is applied to scale realized returns. model
    Source sentence
    We set the annualized volatility target 𝜎tgt to be 15% and estimate the ex‑ante volatility 𝜎(𝑖,straddle)𝑡 with a 20‑day exponentially weighted moving standard deviation…
  • The market is assumed to be frictionless for the purpose of backtesting, aside from the explicitly modeled transaction‑cost component. market
    Source sentence
    Some of the key challenges of rebalancing an options portfolio include market microstructure considerations arising from market liquidity and bid‑ask spreads, which can result in high transaction costs.

Data

Backtest sample: Equities listed on the S&P 100 · options · daily

  • Option‑Metrics Ivy DB database · Option‑Metrics options commercial
    2010‑2023 · Equity options on S&P 100 constituents
    Source sentence
    Our dataset consists of option contracts sourced from the Option‑Metrics Ivy DB database, comprising end‑of‑day bid‑ask prices, implied volatility and Greeks of individual options…
  • CRSP daily stock file · CRSP other commercial
    2010‑2023 · Underlying stocks of S&P 100 constituents
    Source sentence
    We obtain underlying stock prices from the Center for Research in Security Prices (CRSP), which we use for computing option money‑ness and accounting for corporate actions such as stock splits.

Recognised sources: CRSP OptionMetrics IvyDB

Costs

Modeled Costs are part of the reported headline results.

Transaction costs are incorporated via turnover‑adjusted returns with costs ranging from 0 to 50 basis points per trade.

Source sentence
compute Sharpe ratios adjusted for transaction costs by taking into account turnover‑adjusted returns

Finds 2

Reported performance (LSTM deep learning model): Sharpe 1.33 (benchmark 0.70) · annual return 26.6% · max drawdown 27.4%

  • The LSTM deep‑learning model achieves the highest risk‑adjusted performance, with a Sharpe ratio of 1.329 when rescaled to a 15% target volatility. performance
    Source sentence
    (Table 2: Performance Metrics – Rescaled to Target Volatility)
  • Turnover regularization improves LSTM performance under high transaction costs, allowing it to outperform benchmarks up to 50 bps costs. performance
    Source sentence
    turnover regularization further enhances the performance of the LSTM for high transaction costs of 𝑐= 10 to 50 bps, allowing the regularized model to outperform other strategies at prohibitively high levels of transaction costs.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 10 related papers). Coverage is partial, so this is neither replication nor refutation.

Cited by 5 papers in the archive (4 by independent authors)

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (51)

  1. UK List of \TeX Frequently Asked Questions (2019)
  2. The \textsf amsart , \textsf amsproc , and \textsf amsbook document~classes (2004)
  3. a lgorithm2e.sty—package for algorithms (2015)
  4. The algorithms bundle (2009)
  5. The Listings Package (2015)
  6. Publication quality tables in \LaTeX (2005)
  7. ACM Visual Identity Standards (2007)
  8. The subcaption package (2013)
and 43 more
  1. A package to create a nomenclature (2005)
  2. User Manual for glossaries.sty v4.44 (2019)
  3. The \textsl textcase package (2004)
  4. Babel (2022)
  5. Time Series Momentum (2012) — link
  6. Dissecting Investment Strategies in the Cross Section and Time Series (2015)
  7. Spatio-Temporal Momentum : Jointly Learning Time-Series and Cross-Sectional Strategies — → 2302.10175
  8. Enhancing Time-Series Momentum Strategies Using Deep Neural Networks (2019) — link
  9. Slow Momentum with Fast Reversion : A Trading Strategy Using Deep Learning and Changepoint Detection (2022) — link
  10. Trading with the Momentum Transformer : An Intelligent and Interpretable Architecture (2023) — link
  11. Returns to Buying Winners and Selling Losers : Implications for Stock Market Efficiency (1993) — link
  12. International Momentum Strategies (1998)
  13. Momentum in Futures Markets (2005)
  14. Building Cross-Sectional Systematic Strategies by Learning to Rank (2021) — link
  15. Enhancing Cross-Sectional Currency Strategies by Context-Aware Learning to Rank with Self-Attention (2022) — link
  16. Mean Reversion in Stock Prices : Evidence and Implications (1988) — link
  17. Does the Stock Market Overreact ? (1985) — link
  18. Fact and Fantasy in the Use of Options (1975) — link
  19. OCC - Historical Volume Statistics (2024)
  20. The Pricing of Options and Corporate Liabilities (1973)
  21. Theory of Rational Option Pricing (1973) — link
  22. Option Pricing : A Simplified Approach (1979) — link
  23. A Factor Model for Option Returns (2022) — link
  24. Maturity Driven Mispricing of Options (2022) — link
  25. Deep Hedging (2019) — link
  26. Dynamic Replication and Hedging : A Reinforcement Learning Approach (2019) — link
  27. A Nonparametric Approach to Pricing and Hedging Derivative Securities Via Learning Networks (1994) — link
  28. Option Pricing using Machine Learning (2021) — link
  29. Option Return Predictability with Machine Learning and Big Data (2023) — link
  30. Expected Option Returns (2001) — link
  31. Cross-section of Option Returns and Volatility (2009) — link
  32. Equity Volatility Term Structures and the Cross Section of Option Returns (2017) — link
  33. Option Momentum (2023) — link
  34. Who Profits from Trading Options ? (2023) — link
  35. Limits of Arbitrage and Primary Risk-Taking in Derivative Securities (2023) — link
  36. Options Trading Costs Are Lower than You Think (2020) — link
  37. The Sharpe Ratio (1994) — link
  38. The Impact of Volatility Targeting (2018) — link
  39. Long Short-Term Memory (1997) — link
  40. Time Series Forecasting With Deep Learning : A Survey (2021) — link
  41. Autoregressive Convolutional Neural Networks for Asynchronous Time Series (2018)
  42. Adam: A Method for Stochastic Optimization (2014) — link
  43. DeepLOB : Deep Convolutional Neural Networks for Limit Order Books (2019)

1 of 51 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.