Multi-relational Graph Diffusion Neural Network with Parallel Retention for Stock Trends Classification (2401.05430v1)
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).
- “Deep learning for stock prediction using numerical and textual information,” in 15th Int. Conf. on Computer and Information Science (ICIS). IEEE, 2016, pp. 1–6.
- “A deep learning framework for financial time series using stacked autoencoders and long-short term memory,” PloS one, vol. 12, no. 7, pp. e0180944, 2017.
- “Knowledge-driven stock trend prediction and explanation via temporal convolutional network,” in World Wide Web Conference (WWW), Companion Proceedings, 2019, pp. 678–685.
- “Stock movement prediction from tweets and historical prices,” in 56th Ann. Meeting Assoc. for Computational Linguistics, 2018, vol. 1, pp. 1970–1979.
- “Accurate multivariate stock movement prediction via data-axis transformer with multi-level contexts,” in Knowledge Discovery & Data Mining (KDD), 2021, pp. 2037–2045.
- “HATS: A hierarchical graph attention network for stock movement prediction,” arXiv preprint arXiv:1908.07999, 2019.
- “Temporal and heterogeneous graph neural network for financial time series prediction,” in 31st ACM Int. Conf. on Information & Knowledge Management, 2022, pp. 3584–3593.
- “Hierarchical multi-scale gaussian transformer for stock movement prediction.,” in IJCAI, 2020, pp. 4640–4646.
- “EvolveGCN: Evolving graph convolutional networks for dynamic graphs,” in AAAI, 2020, pp. 5363–5370.
- “Traffic flow prediction via spatial temporal graph neural network,” in The Web Conference (WWW), 2020, pp. 1082–1092.
- Ruey S Tsay, Analysis of financial time series, John Wiley & Sons, 2005.
- “Efficient integration of multi-order dynamics and internal dynamics in stock movement prediction,” in Web Search and Data Mining (WSDM), 2023, pp. 850–858.
- “Exploring the scale-free nature of stock markets: Hyperbolic graph learning for algorithmic trading,” in The Web Conference (WWW), 2021, pp. 11–22.
- “Towards deeper graph neural networks,” in Knowledge Discovery & Data Mining (KDD), 2020, pp. 338–348.
- “A dual-stage attention-based recurrent neural network for time series prediction,” arXiv preprint arXiv:1704.02971, 2017.
- “Risk prediction and evaluation of transnational transmission of financial crisis based on complex network,” Cluster Computing, vol. 22, pp. 4307–4313, 2019.
- “Graph wavenet for deep spatial-temporal graph modeling,” arXiv preprint arXiv:1906.00121, 2019.
- “Multivariate time-series forecasting with temporal polynomial graph neural networks,” in NeurIPS, 2022, pp. 19414–19426.
- “A global network topology of stock markets: Transmitters and receivers of spillover effects,” Physica A: Statistical Mechanics and its Applications, vol. 492, pp. 2136–2153, 2018.
- “Herd behavior and aggregate fluctuations in financial markets,” Macroeconomic Dynamics, vol. 4, no. 2, pp. 170–196, 2000.
- “Information transfer between stock market sectors: A comparison between the usa and china,” Entropy, vol. 22, no. 2, pp. 194, 2020.
- “Semi-supervised classification with graph convolutional networks,” arXiv preprint arXiv:1609.02907, 2016.
- “Graph attention networks,” arXiv preprint arXiv:1710.10903, 2017.
- “Measuring and relieving the over-smoothing problem for graph neural networks from the topological view,” in AAAI, 2020, pp. 3438–3445.
- “Diffusion improves graph learning,” in NeurIPS, 2019, pp. 13333–13345.
- “Decoupling the depth and scope of graph neural networks,” in NeurIPS, 2021, pp. 19665–19679.
- “Retentive network: A successor to transformer for large language models,” arXiv preprint arXiv:2307.08621, 2023.
- “DGDNN: Decoupled graph diffusion neural network for stock movement prediction,” in 16th Int. Conf. on Agents and Artificial Intelligence (ICAART), Feb 2024.
- “Stock market volatility and learning,” The Journal of finance, vol. 71, no. 1, pp. 33–82, 2016.
- Zinuo You (4 papers)
- Pengju Zhang (14 papers)
- Jin Zheng (24 papers)
- John Cartlidge (19 papers)