Mamba Meets Financial Markets: A Graph-Mamba Approach for Stock Price Prediction

2024-09-26

arXiv.org

AI Summary

To address the high computational cost of traditional Transformers and their difficulty in modeling long-term temporal dependencies and cross-stock correlations in stock price forecasting, this paper proposes Mamba-GNN—the first framework integrating the state-space model Mamba with graph neural networks (GNNs). Methodologically, it employs bidirectional Mamba blocks to capture long-range temporal dependencies and introduces adaptive graph convolution to model dynamic inter-stock relationships at the daily level, constructing a financial time-series graph structure. Experiments on multiple real-world stock datasets demonstrate that Mamba-GNN significantly outperforms state-of-the-art methods, achieving substantial improvements in prediction accuracy. Moreover, it maintains near-linear time complexity, enabling efficient real-time inference. Thus, Mamba-GNN achieves a favorable trade-off between predictive accuracy and computational efficiency.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Stock markets play an important role in the global economy, where accurate stock price predictions can lead to significant financial returns. While existing transformer-based models have outperformed long short-term memory networks and convolutional neural networks in financial time series prediction, their high computational complexity and memory requirements limit their practicality for real-time trading and long-sequence data processing. To address these challenges, we propose SAMBA, an innovative framework for stock return prediction that builds on the Mamba architecture and integrates graph neural networks. SAMBA achieves near-linear computational complexity by utilizing a bidirectional Mamba block to capture long-term dependencies in historical price data and employing adaptive graph convolution to model dependencies between daily stock features. Our experimental results demonstrate that SAMBA significantly outperforms state-of-the-art baseline models in prediction accuracy, maintaining low computational complexity. The code and datasets are available at github.com/Ali-Meh619/SAMBA.

Problem

• Stock Price Prediction
• Accuracy Improvement
• Computational Resource Reduction

Innovation

• SAMBA method
• Graph Neural Networks
• Efficient Computational Resource