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

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. NTRODUCTION The stock market is an essential component of a broad and intricate financial system, and stock prices reflect the dynamics of economic and financial activities. Predicting future movements of either individual stocks or overall market indices is important to investors and other market players [1], which requires significant efforts but lacks satisfactory results. Conventional approaches vary from fundamental and technical analysis to linear statistical models, such as Momentum Strategies and Autoregressive Integrated Moving Average (ARIMA), which capture simple short-term patterns from historical prices. With the tremendous power and success in exploring the nonlinear relationship and dealing with big data, machine learning and neural networks are increasingly utilized in stock movement prediction and have shown better results in prediction accuracy over traditional methods [2].