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

Paper: arXiv 2302.14164

Authors: Jingyi Gu, Fadi P. Deek, Guiling Wang

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.

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 7.5/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper introduces a novel Wasserstein GAN framework tailored for multi-step stock prediction by incorporating news sentiment, market volatility, and a sequence-to-sequence attentive network. Empirical evaluation is strong, utilizing real-world index data with comprehensive baseline comparisons and ablation studies.

Research Flowchart

  flowchart TD
    A[Goal: Multi-step Stock Index Trend Prediction] --> B[Data Inputs: Stock Prices, News Context & Market Sentiment]
    B --> C[Attentive Seq2Seq Model: Captures Temporal Dependencies]
    C --> D[IndexGAN Framework: Wasserstein GAN with Critic Distance]
    D --> E[Deployment: Rolling Strategy to Mitigate Market Noise]
    E --> F[Outcomes: Outperforms SOTA Baselines & Prevents Mode Collapse]