Stockformer: A price–volume factor stock selection model based on wavelet transform and multi-task self-attention networks

Abstract

As the Chinese stock market continues to evolve and its market structure grows increasingly complex, traditional quantitative trading methods face escalating challenges. Due to policy uncertainty and frequent market fluctuations triggered by sudden economic events, existing models often struggle to predict market dynamics accurately. To address these challenges, this paper introduces “Stockformer,” a price–volume factor stock selection model that integrates wavelet transformation and a multitask self-attention network to enhance responsiveness and predictive accuracy regarding market instabilities. Through discrete wavelet transform, Stockformer decomposes stock returns into high and low frequencies, meticulously capturing long-term market trends and short-term fluctuations, including abrupt events. Moreover, the model incorporates a Dual-Frequency Spatiotemporal Encoder and graph embedding techniques to capture complex temporal and spatial relationships among stocks effectively. Employing a multitask learning strategy, it simultaneously predicts stock returns and directional trends. Experimental results show that Stockformer outperforms existing advanced methods on multiple real stock market datasets. In strategy backtesting, Stockformer consistently demonstrates exceptional stability and reliability across market conditions—whether rising, falling, or fluctuating—particularly maintaining high performance during downturns or volatile periods, indicating high adaptability to market fluctuations. To foster innovation and collaboration in the financial analysis sector, the Stockformer model’s code has been open-sourced and is available on the GitHub repository: https://github.com/Eric991005/Multitask-Stockformer.