Trader-Company Method: A Metaheuristics for Interpretable Stock Price Prediction

Investors try to predict returns of nancial assets to make successful investment. Many quantitative analysts have used machine learning-based methods to nd unknown pro table market rules from large amounts of market data. However, there are several challenges in nancial markets hindering practical applications of machine learning-based models. First, in nancial markets, there is no single model that can consistently make accurate prediction because traders in markets quickly adapt to newly available information. Instead, there are a number of ephemeral and partially correct models called "alpha factors". Second, since nancial markets are highly uncertain, ensuring interpretability of prediction models is quite important to make reliable trading strategies. To overcome these challenges, we propose the Trader-Company method, a novel evolutionary model that mimics the roles of a nancial institute and traders belonging to it. Our method predicts future stock returns by aggregating suggestions from multiple weak learners called Traders. A Trader holds a collection of simple mathematical formulae, each of which represents a candidate of an alpha factor and would be interpretable for real-world investors. The aggregation algorithm, called a Company, maintains multiple Traders. By randomly generating new Traders and retraining them, Companies can e ciently nd nancially meaningful formulae whilst avoiding over tting to a transient state of the market. We show the e ectiveness of our method by conducting experiments on real market data.