Relational Stock Selection via Probabilistic State Space Learning
- 28 November 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (2) , 865-880
Abstract
Optimizing stock selection through stock ranking is one of the critical but intricate tasks in quantitative trading areas because of the non-stationary dynamics and complicated interdependencies behind stock markets. Recent studies have made efforts to model historical market movements to enhance stock selection. However, they primarily borrowed the spirit of time series modeling and sought to build a deterministic paradigm without considering the uncertain fluctuations. In addition, some of these studies tailor to explore stock correlations from a predefined (e.g., binary) graph structure and use explicitly simple relations (such as first-order relations) to guide evolving interactions. Nevertheless, aggregating predefined but shallow relationships to collaborate with stock movements may affect selection generalizability and increase the risk of portfolio failure. This study introduces a novel R elational stock selection framework via probabilistic S tate S pace L earning (or RSSL ) for stock selection. Specifically, RSSL first attempts to build a tree-based structure to explicitly expose higher-order relations in the stock market, primarily by discovering a hierarchical delineation of ties between stocks. Whereafter, it couples with time-varying movements via an attention mechanism to smoothly explore the interactive correlations among different stocks. Inspired by recent state space models (SSM) in probabilistic Bayesian learning, we devise a Probabilistic Kalman Network (PKNet) with uncertainty estimates to recursively simulate ever-changing stock volatility, enabling more promising return-risk trade-offs. The experimental results on several real-world stock market datasets demonstrate that RSSL outperforms several representative baseline methods by a significant margin.Keywords
Funding Information
- National Natural Science Foundation of China (62102326, 72471197, 62376228)
- Natural Science Foundation of Sichuan Province (2023NSFSC1411, 25QNJJ0627)
- Sichuan Science and Technology Program (2023ZYD0145)
- Chengdu Municipal Science and Technology Program (2023-JB00-00016-GX)
- Central Universities (JBK2406078)
- Guanghua Talent Project, piHealth Inc
- Food and Drug Administration
This publication has 43 references indexed in Scilit:
- Stock Movement Prediction Based on Bi-Typed Hybrid-Relational Market Knowledge Graph Via Dual Attention NetworksIEEE Transactions on Knowledge and Data Engineering, 2022
- HATR-I: Hierarchical Adaptive Temporal Relational Interaction for Stock Trend PredictionIEEE Transactions on Knowledge and Data Engineering, 2022
- Deep learning in the stock market—a systematic survey of practice, backtesting, and applicationsArtificial Intelligence Review, 2022
- Applications of deep learning in stock market prediction: Recent progressExpert Systems with Applications, 2021
- FinGAT: Financial Graph Attention Networks for Recommending Top-K Profitable StocksIEEE Transactions on Knowledge and Data Engineering, 2021
- Stock market movement forecast: A Systematic reviewExpert Systems with Applications, 2020
- Shared analyst coverage: Unifying momentum spillover effectsJournal of Financial Economics, 2020
- CNNpred: CNN-based stock market prediction using a diverse set of variablesExpert Systems with Applications, 2019
- Understanding the Basis of the Kalman Filter Via a Simple and Intuitive Derivation [Lecture Notes]IEEE Signal Processing Magazine, 2012
- A hybrid ARIMA and support vector machines model in stock price forecastingOmega, 2005