LSR-IGRU: Stock Trend Prediction Based on Long Short-Term Relationships and Improved GRU

Paper: arXiv 2409.08282

Abstract

Stock price prediction is a challenging problem in the field of finance and receives widespread attention. In recent years, with the rapid development of technologies such as deep learning and graph neural networks, more research methods have begun to focus on exploring the interrelationships between stocks. However, existing methods mostly focus on the short-term dynamic relationships of stocks and directly integrating relationship information with temporal information. They often overlook the complex nonlinear dynamic characteristics and potential higher-order interaction relationships among stocks in the stock market. Therefore, we propose a stock price trend prediction model named LSR-IGRU in this paper, which is based on long short-term stock relationships and an improved GRU input. Firstly, we construct a long short-term relationship matrix between stocks, where secondary industry information is employed for the first time to capture long-term relationships of stocks, and overnight price information is utilized to establish short-term relationships. Next, we improve the inputs of the GRU model at each step, enabling the model to more effectively integrate temporal information and long short-term relationship information, thereby significantly improving the accuracy of predicting stock trend changes. Finally, through extensive experiments on multiple datasets from stock markets in China and the United States, we validate the superiority of the proposed LSR-IGRU model over the current state-of-the-art baseline models. We also apply the proposed model to the algorithmic trading system of a financial company, achieving significantly higher cumulative portfolio returns compared to other baseline methods. Our sources are released at https://github.com/ZP1481616577/Baselines_LSR-IGRU.

Complexity vs Empirical Score

• Math Complexity: 7.0/10
• Empirical Rigor: 6.0/10 (capped from 8.5: transaction costs not modelled; see penalty flags)
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced deep learning architectures (GRU, graph neural networks) with novel relationship matrices, indicating high mathematical complexity. It also demonstrates strong empirical rigor through extensive experiments on real-world stock market datasets (China and US), deployment in an algorithmic trading system, and release of source code.

Research Flowchart

  flowchart TD
  A["Research Goal: Improve Stock Trend Prediction by Integrating Long/Short-Term Relationships with Temporal Data"] --> B["Data Processing"]
  B --> C["Construct Long Short-Term Relationship Matrix"]
  B --> D["Input Financial Time Series Data"]
  C --> E["Improved GRU Model"]
  D --> E
  E --> F["Model Training & Prediction"]
  F --> G["Outcomes"]
  
  subgraph G ["Key Findings"]
      G1["Superior accuracy vs SOTA baselines"]
      G2["Higher cumulative returns in algorithmic trading"]
  end
  
  C --> C1["Long-term: Secondary Industry Info"]
  C --> C2["Short-term: Overnight Price Info"]
  E --> E1["Enhanced GRU Input Integration"]

Cited References (56)

1. Stock market autoregressive dynamics: a multinational comparative study with quantile regression (2016)
2. Hidden Markov models for speech recognition (1991)
3. Forecasting stock market movement direction with support vector machine (2005)
4. Financial time series forecasting using support vector machines (2003)
5. Forecasting with artificial neural networks:: The state of the art (1998)
6. How effective are neural networks at forecasting and prediction? A review and evaluation (1998)
7. Predicting stock market index using fusion of machine learning techniques (2015)
8. StockNet—GRU based stock index prediction (2022)

2 of 56 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.