Paper: arXiv 2401.05430

Abstract

Stock trend classification remains a fundamental yet challenging task, owing to the intricate time-evolving dynamics between and within stocks. To tackle these two challenges, we propose a graph-based representation learning approach aimed at predicting the future movements of multiple stocks. Initially, we model the complex time-varying relationships between stocks by generating dynamic multi-relational stock graphs. This is achieved through a novel edge generation algorithm that leverages information entropy and signal energy to quantify the intensity and directionality of inter-stock relations on each trading day. Then, we further refine these initial graphs through a stochastic multi-relational diffusion process, adaptively learning task-optimal edges. Subsequently, we implement a decoupled representation learning scheme with parallel retention to obtain the final graph representation. This strategy better captures the unique temporal features within individual stocks while also capturing the overall structure of the stock graph. Comprehensive experiments conducted on real-world datasets from two US markets (NASDAQ and NYSE) and one Chinese market (Shanghai Stock Exchange: SSE) validate the effectiveness of our method. Our approach consistently outperforms state-of-the-art baselines in forecasting next trading day stock trends across three test periods spanning seven years. Datasets and code have been released (https://github.com/pixelhero98/MGDPR).

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 8.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced graph theory, diffusion processes, and signal processing (entropy/energy formulas) with extensive real-world data across multiple markets, released code, and backtested baselines.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Predict Next-Day Stock Trends<br>Modeling Time-Evolving Inter-Stock Dynamics"] --> B["Input Data<br>Real-world markets: NASDAQ, NYSE, SSE"]

  B --> C["Graph Construction<br>Dynamic Multi-Relational Graph Generation<br>using Info Entropy & Signal Energy"]

  C --> D["Adaptive Refinement<br>Stochastic Multi-Relational Diffusion Process<br>Learn task-optimal edges"]

  D --> E["Representation Learning<br>Decoupled Scheme with Parallel Retention<br>Capture temporal & structural features"]

  E --> F["Output & Findings<br>Stock Trend Classification<br>Consistent SOTA Outperformance over 7 Years"]

Cited References (29)

  1. Deep learning for stock prediction using numerical and textual information (2016)
  2. Stock movement prediction from tweets and historical prices (2018)
  3. Temporal and Heterogeneous Graph Neural Network for Financial Time Series Prediction — → 2305.08740
  4. Information transfer between stock market sectors: A comparison between the USA and China (2020)
  5. Risk prediction and evaluation of transnational transmission of financial crisis based on complex network (2019)
  6. Decoupling the depth and scope of graph neural networks (2021)
  7. A deep learning framework for financial time series using stacked autoencoders and long-short term memory (2017)
  8. Knowledge-driven stock trend prediction and explanation via temporal convolutional network (2019)
and 21 more
  1. EvolveGCN : Evolving graph convolutional networks for dynamic graphs (2020)
  2. Traffic flow prediction via spatial temporal graph neural network (2020)
  3. Efficient integration of multi-order dynamics and internal dynamics in stock movement prediction (2023)
  4. HATS : A hierarchical graph attention network for stock movement prediction (2019) — link
  5. Analysis of financial time series (2005)
  6. Accurate multivariate stock movement prediction via data-axis transformer with multi-level contexts (2021)
  7. Hierarchical Multi-Scale Gaussian Transformer for Stock Movement Prediction. (2020)
  8. Exploring the scale-free nature of stock markets: Hyperbolic graph learning for algorithmic trading (2021)
  9. A global network topology of stock markets: Transmitters and receivers of spillover effects (2018)
  10. Herd behavior and aggregate fluctuations in financial markets (2000)
  11. Semi-supervised classification with graph convolutional networks (2016) — link
  12. Graph attention networks (2017) — link
  13. Measuring and relieving the over-smoothing problem for graph neural networks from the topological view (2020)
  14. Diffusion improves graph learning (2019)
  15. Towards deeper graph neural networks (2020)
  16. Retentive Network: A Successor to Transformer for Large Language Models (2023) — link
  17. A dual-stage attention-based recurrent neural network for time series prediction (2017) — link
  18. Graph wavenet for deep spatial-temporal graph modeling (2019) — link
  19. Multivariate time-series forecasting with temporal polynomial graph neural networks (2022)
  20. Stock market volatility and learning (2016)
  21. DGDNN : Decoupled Graph Diffusion Neural Network for Stock Movement Prediction (2024)

1 of 29 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.