Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning-based framework for generating synergistic sets of formulaic alpha signals in quantitative trading, optimizing their combined performance for improved stock trend forecasting and investment returns.

Contribution

It presents a novel alpha-mining framework that directly optimizes for the performance of alpha combinations using reinforcement learning, unlike traditional methods that mine alphas individually.

Findings

Achieves higher stock trend forecasting accuracy.

Demonstrates improved investment returns.

Efficient exploration of alpha search space.

Abstract

In the field of quantitative trading, it is common practice to transform raw historical stock data into indicative signals for the market trend. Such signals are called alpha factors. Alphas in formula forms are more interpretable and thus favored by practitioners concerned with risk. In practice, a set of formulaic alphas is often used together for better modeling precision, so we need to find synergistic formulaic alpha sets that work well together. However, most traditional alpha generators mine alphas one by one separately, overlooking the fact that the alphas would be combined later. In this paper, we propose a new alpha-mining framework that prioritizes mining a synergistic set of alphas, i.e., it directly uses the performance of the downstream combination model to optimize the alpha generator. Our framework also leverages the strong exploratory capabilities of reinforcement learning~(RL) to better explore the vast search space of formulaic alphas. The contribution to the combination models' performance is assigned to be the return used in the RL process, driving the alpha generator to find better alphas that improve upon the current set. Experimental evaluations on real-world stock market data demonstrate both the effectiveness and the efficiency of our framework for stock trend forecasting. The investment simulation results show that our framework is able to achieve higher returns compared to previous approaches.