---
title: Relationship between deep hedging and delta hedging: leveraging a statistical arbitrage strategy
url: https://www.ml-quant.com/papers/ssrn/4628845/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4628845
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4628845
featured: 2023-11-15
citations: 0
topic: Derivatives & Volatility
---


# Relationship between deep hedging and delta hedging: leveraging a statistical arbitrage strategy

The research examines the link between deep and delta hedging, suggesting a risk-minimizing strategy that combines both with statistical arbitrage, and discusses the effects of statistical arbitrages on deep hedging.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4628845
- Identifier: SSRN 4628845
- Released: 2023-11-10
- First featured: Quant Letter No. 26 (2023-11-15): https://www.ml-quant.com/issues/2023-11-15/
- Citations (Semantic Scholar): 0
- Published in: not yet
- Topic: Derivatives & Volatility

## Related

- [Is the difference between deep hedging and delta hedging a statistical arbitrage?](https://www.ml-quant.com/papers/arxiv/2407.14736/): The research compares deep hedging and delta hedging in a GARCH-based market model, suggesting that the difference between the two can be a statistical arbitrage if the risk measure doesn't adequately consider negative outcomes.
- [Statistical Arbitrage vs. Delta Hedging](https://www.ml-quant.com/papers/ssrn/4899809/): Horikawa and Nakagawa's 2024 study suggests that deep hedging can have a speculative aspect, which can be mitigated by choosing the right risk measure.
- [Deeper Hedging: A New Agent-based Model for Effective Deep Hedging](https://www.ml-quant.com/papers/doi/10-1145-3604237-3626913/): The Chiarella-Heston model, an advanced agent-based model, enhances deep hedging strategies by incorporating different types of traders, and performs better in creating realistic financial time series than three other models.
- [Adversarial Deep Hedging: Learning to Hedge without Price Process Modeling](https://www.ml-quant.com/papers/arxiv/2307.13217/): The study introduces adversarial deep hedging, a new method for derivative hedging in incomplete markets, performing well across various real market data without explicit modeling.
- [Efficient Learning of Nested Deep Hedging using Multiple Options](https://www.ml-quant.com/papers/arxiv/2305.12264/): Study proposes nested deep hedging method for derivatives with market frictions using neural networks.
- [Enhancing Deep Hedging of Options with Implied Volatility Surface Feedback Information](https://www.ml-quant.com/papers/arxiv/2407.21138/): A new hedging strategy for S&P 500 options is introduced, using a unique reinforcement learning algorithm and hybrid neural network, which performs better than traditional benchmarks in tests and simulations.