Quantformer: from attention to profit with a quantitative transformer trading strategy

2024-03-30

AI Summary

Quantitative trading faces challenges in dynamically modeling evolving markets and effectively fusing heterogeneous signals from multiple data sources. Method: This paper proposes Quantformer—the first quantitative model to systematically integrate the Transformer architecture into factor construction. It innovatively transfers pre-trained sentiment analysis capabilities to numerical financial time-series processing, jointly modeling market sentiment and multi-source structured market data to capture long-range dependencies and enhance factors with explicit profit orientation. The model employs rolling-window training, cross-stock joint feature learning, and end-to-end return prediction. Contribution/Results: Evaluated on 4,601 A-share stocks from 2010–2019 (over 5 million samples), Quantformer’s generated investment factors significantly outperform 100 mainstream factor strategies in predictive accuracy, while substantially improving trading signal precision. It establishes a novel paradigm for deep learning–based quantitative factor modeling that is both interpretable and highly robust.

Technology Category

• Machine Learning: Quantum Machine Learning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

In traditional quantitative trading practice, navigating the complicated and dynamic financial market presents a persistent challenge. Fully capturing various market variables, including long-term information, as well as essential signals that may lead to profit remains a difficult task for learning algorithms. In order to tackle this challenge, this paper introduces quantformer, an enhanced neural network architecture based on transformers, to build investment factors. By transfer learning from sentiment analysis, quantformer not only exploits its original inherent advantages in capturing long-range dependencies and modeling complex data relationships, but is also able to solve tasks with numerical inputs and accurately forecast future returns over a given period. This work collects more than 5,000,000 rolling data of 4,601 stocks in the Chinese capital market from 2010 to 2019. The results of this study demonstrated the model's superior performance in predicting stock trends compared with other 100 factor-based quantitative strategies. Notably, the model's innovative use of transformer-liked model to establish factors, in conjunction with market sentiment information, has been shown to enhance the accuracy of trading signals significantly, thereby offering promising implications for the future of quantitative trading strategies.

Problem

• Predicting stock returns using transformer-based neural networks
• Capturing long-range dependencies and market variables effectively
• Enhancing trading signal accuracy with sentiment transfer learning

Innovation

• Transformer-based neural network for trading factors
• Transfer learning from sentiment analysis application
• Captures long-range dependencies and complex relationships