Stock Broad-Index Trend Patterns Learning via Domain Knowledge Informed Generative Network

TL;DR

This paper introduces IndexGAN, a novel generative network that incorporates domain knowledge, news context, and multi-step prediction to improve stock market trend forecasting, addressing limitations of existing GAN-based methods.

Contribution

The paper presents IndexGAN, the first to formulate stock prediction within a Wasserstein GAN framework with multi-step forecasting and news integration, enhancing prediction accuracy.

Findings

Outperforms state-of-the-art baselines in real-world experiments

Effectively incorporates news and market sentiment

Reduces noise through a rolling deployment strategy

Abstract

Predicting the Stock movement attracts much attention from both industry and academia. Despite such significant efforts, the results remain unsatisfactory due to the inherently complicated nature of the stock market driven by factors including supply and demand, the state of the economy, the political climate, and even irrational human behavior. Recently, Generative Adversarial Networks (GAN) have been extended for time series data; however, robust methods are primarily for synthetic series generation, which fall short for appropriate stock prediction. This is because existing GANs for stock applications suffer from mode collapse and only consider one-step prediction, thus underutilizing the potential of GAN. Furthermore, merging news and market volatility are neglected in current GANs. To address these issues, we exploit expert domain knowledge in finance and, for the first time, attempt to formulate stock movement prediction into a Wasserstein GAN framework for multi-step prediction. We propose IndexGAN, which includes deliberate designs for the inherent characteristics of the stock market, leverages news context learning to thoroughly investigate textual information and develop an attentive seq2seq learning network that captures the temporal dependency among stock prices, news, and market sentiment. We also utilize the critic to approximate the Wasserstein distance between actual and predicted sequences and develop a rolling strategy for deployment that mitigates noise from the financial market. Extensive experiments are conducted on real-world broad-based indices, demonstrating the superior performance of our architecture over other state-of-the-art baselines, also validating all its contributing components.