Extreme Stock Fluctuation Early Warning Model Based on Causal Inference and Machine Learning
Main Article Content
Abstract
Large price swings increase portfolio risk and make trading decisions difficult. This study builds a short-term warning model that uses Granger-based feature selection and a LightGBM classifier tuned with Bayesian search. The model is tested on three years of CSI 300 data. Daily log-returns are used to mark extreme events, and all evaluation follows time order to avoid future information. The model signaled about 70% of large price swings two trading days in advance and showed better results than a model without causal features. These findings indicate that adding predictors with leading effects helps identify warning signs before sharp movements. The framework can support routine risk control and position planning.
Article Details
Section
How to Cite
References
1. M. Prata, G. Masi, L. Berti, V. Arrigoni, A. Coletta, I. Cannistraci, and N. Bartolini, "Lob-based deep learning models for stock price trend prediction: A benchmark study," Artificial Intelligence Review, vol. 57, no. 5, p. 116, 2024. doi: 10.1007/s10462-024-10715-4
2. J. Yang, Y. Li, D. Harper, I. Clarke, and J. Li, "Macro financial prediction of cross border real estate returns using XGBoost LSTM models," Journal of Artificial Intelligence and Information, vol. 2, pp. 113-118, 2025.
3. C. Li, D. Song, and D. Tao, "Multi-task recurrent neural networks and higher-order Markov random fields for stock price movement prediction: Multi-task RNN and higher-order MRFs for stock price classification," In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, July, 2019, pp. 1141-1151.
4. J. Whitmore, P. Mehra, J. Yang, and E. Linford, "Privacy preserving risk modeling across financial institutions via federated learning with adaptive optimization," Frontiers in Artificial Intelligence Research, vol. 2, no. 1, pp. 35-43, 2025.
5. X. Xiao, A. Li, B. Kchouri, and S. Shan, "Tracing the dynamic impact of energy transitions on equity market volatility in an era of financial turbulence," Energy Economics, vol. 133, p. 107443, 2024. doi: 10.1016/j.eneco.2024.107443
6. S. Samantaray, S. Mohapatra, and M. Mishra, "High-precision forecasting of Indian stock market indices using weighted ensemble of hyperparameter-tuned LightGBM models with diverse technical indicators," Systems Science & Control Engineering, vol. 13, no. 1, p. 2567887, 2025. doi: 10.1080/21642583.2025.2567887
7. Z. Liu, "Stock volatility prediction using LightGBM based algorithm," In 2022 International Conference on Big Data, Information and Computer Network (BDICN), January, 2022, pp. 283-286. doi: 10.1109/bdicn55575.2022.00061
8. M. S. A. Dolon, "Deployment and performance evaluation of hybrid machine learning models for stock price forecasting and risk prediction in volatile markets," American Journal of Scholarly Research and Innovation, vol. 4, no. 01, pp. 287-319, 2025.
9. S. S. M. Asif, "Create an AI-based model for dynamic risk management in equity portfolios that accounts for extreme market events (eg, pandemics, financial crises)," 2024.
10. Q. Hu, X. Li, Z. Li, and Y. Zhang, "Generative AI of Pinecone vector retrieval and retrieval-augmented generation architecture: Financial data-driven intelligent customer recommendation system," 2025. doi: 10.20944/preprints202510.1197.v1
11. W. Sun, “Integration of market-oriented development models and marketing strategies in real estate,” European Journal of Business, Economics & Management, vol. 1, no. 3, pp. 45–52, 2025.
12. W. Zhu, and J. Yang, "Causal assessment of cross-border project risk governance and financial compliance: A hierarchical panel and survival analysis approach based on H Company's overseas projects," 2025. doi: 10.20944/preprints202509.1175.v1
13. J. Wang, and Y. Xiao, "Assessing the spillover effects of marketing promotions on credit risk in consumer finance: An empirical study based on AB testing and causal inference," 2025.
14. M. Devan, K. Thirunavukkarasu, and L. Shanmugam, "Algorithmic trading strategies: Real-time data analytics with machine learning," Journal of Knowledge Learning and Science Technology, vol. 2, no. 3, pp. 522-546, 2023. doi: 10.60087/jklst.vol2.n3.p546
15. W. Y. Pang, and L. Lin, "Market state transitions and crash early warning in the Chinese stock market," 2025.
16. T. Li, S. Liu, E. Hong, and J. Xia, "Human resource optimization in the hospitality industry: Big data forecasting and cross-cultural engagement," 2025.
17. S. K. U. Zaman, A. I. Jehangiri, T. Maqsood, A. I. Umar, M. A. Khan, N. Z. Jhanjhi, and M. Masud, "COME-UP: Computation offloading in mobile edge computing with LSTM-based user direction prediction," Applied Sciences, vol. 12, no. 7, p. 3312, 2022.
18. S. Li, "Momentum, volume and investor sentiment study for US technology sector stocks-A hidden Markov model-based principal component analysis," PLoS One, vol. 20, no. 9, p. e0331658, 2025.
19. A. Ang, and A. Timmermann, "Regime changes and financial markets," Annual Review of Financial Economics, vol. 4, no. 1, pp. 313-337, 2012. doi: 10.1146/annurev-financial-110311-101808
20. R. Stuart-Smith, R. Studebaker, M. Yuan, N. Houser, and J. Liao, "Viscera/L: Speculations on an embodied, additive and subtractive manufactured architecture," In Traits of Postdigital Neobaroque: Pre-Proceedings (PDNB). Universitat Innsbruck., 2022.