← Back
Evidence source 6170Spot Checked

Statistical arbitrage powered by Explainable Artificial Intelligence

Unknown venue2022-06-09Paper
Executive summary

Machine learning and explainable AI improve statistical arbitrage trading strategies for S&P500 stocks, enhancing returns and reducing risk.

What it examines

This paper proposes a machine learning approach powered by explainable AI techniques integrated into a statistical arbitrage trading pipeline. It aims to improve prediction performance and portfolio management by discarding irrelevant features, using historical data from S&P500 stocks.

What it concludes

The research shows that explainable AI can enhance financial trading strategies by improving prediction accuracy and reducing risk. Future work could explore dynamic feature selection and the impact of transaction costs. Potential applications include more robust and transparent financial trading systems.

Extracted from this source

Evidence objects

Evidence 745778% extraction confidence
The research shows that explainable AI can enhance financial trading strategies by improving prediction accuracy and reducing risk. Future work could explore dynamic feature selection and the impact of transaction costs. Potential applications include more robust and transparent financial trading systems.

key_findings bullet 1 · key_findings · validation V0

Raw abstract and provenance

Machine learning techniques have recently become the norm for detecting patterns in financial markets. However, relying solely on machine learning algorithms for decision-making can have negative consequences, especially in a critical domain such as the financial one. On the other hand, it is well-known that transforming data into actionable insights can pose a challenge even for seasoned practitioners, particularly in the financial world. Given these compelling reasons, this work proposes a machine learning approach powered by eXplainable Artificial Intelligence techniques integrated into a statistical arbitrage trading pipeline. Specifically, we propose three methods to discard irrelevant features for the prediction task. We evaluate the approaches on historical data of component stocks of the S&P500 index and aim at improving not only the prediction performance at the stock level but also overall at the stock set level. Our analysis shows that our trading strategies that include such feature selection methods improve the portfolio performances by providing predictive signals whose information content suffices and is less noisy than the one embedded in the whole feature set. By performing an in-depth risk-return analysis, we show that the proposed trading strategies powered by explainable AI outperform highly competitive trading strategies considered as baselines.

Source row: 1819 · abstract type: unknown