Research on the Time-Varying Mechanism of Market Sentiment of Artificial Intelligence Industry Stocks Based on Multi-Factor PCA-HMM Framework
Main Article Content
Abstract
The artificial intelligence (AI) sector has become one of the most active areas in financial markets, where investor mood and trading activity strongly affect price changes. This study uses a multi-factor Principal Component Analysis-Hidden Markov Model (PCA-HMM) to examine how sentiment, trading volume, and momentum influence stock returns in the U.S. AI market from 2017 to 2025. Weekly data from 40 listed companies across cloud computing, semiconductor, and autonomous driving industries are analyzed. Principal Component Analysis is used to extract common factors from financial and macroeconomic variables, and the Hidden Markov Model is used to identify market states and their transitions. The results show that sentiment explains about 48% of the variation in returns and plays a stronger role than trading volume or momentum. Momentum has little effect and turns negative during volatile periods. The PCA-HMM model divides the market into stable and turbulent phases lasting between 6 and 12 weeks. The findings show that market sentiment is a main source of fluctuation in AI-related stocks and that the state-based model can be used to track market cycles and assess risk. Future studies should include cross-country data and higher-frequency observations to test the model's wider use.
Article Details
Section
How to Cite
References
1. K. C. Rath, D. Mishra, S. K. T. Tripathy, B. K. Mishra, and K. Muduli, "Potential of AI, quantum computing, and semiconductor technology adoption in future industries: Scope, challenges, and opportunities," Integration of AI, Quantum Computing, and Semiconductor Technology, pp. 415-440, 2025.
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. E. Mathiesen, and J. Paledzki, "AI investment announcements and stock market performance: A comparative study across sectors in the United States," 2025.
4. M. A. Hossain, "Artificial intelligence-driven financial analytics models for predicting market risk and investment decisions in," 2025.
5. 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.
6. L. Oelschläger, and T. Adam, "Detecting bearish and bullish markets in financial time series using hierarchical hidden Markov models," Statistical Modelling, vol. 23, no. 2, pp. 107-126, 2023.
7. P. Celestin, "Principal component analysis for simplifying multivariate financial data in portfolio risk analysis," Principal Component Analysis for Simplifying Multivariate Financial Data in Portfolio Risk Analysis, 2025.
8. 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.
9. E. W. Park, "Principal component analysis and hidden Markov model for forecasting stock returns," arXiv preprint arXiv:2307.00459, 2023.
10. R. H. Weber, and M. Burri, "Classification of services in the digital economy," Springer Science & Business Media, vol. 53, 2012. doi: 10.1007/978-3-642-31635-7
11. M. Wang, Y. H. Lin, and I. Mikhelson, "Regime-switching factor investing with hidden Markov models," Journal of Risk and Financial Management, vol. 13, no. 12, p. 311, 2020.
12. 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.
13. W. Zhu, J. Yang, and Y. Yao, "How cross-departmental collaboration structures mitigate cross-border compliance risks: Network causal inference based on ManpowerGroup's staffing projects," 2025. doi: 10.20944/preprints202510.1339.v1
14. J. Wang, and Y. Xiao, "Application of multi-source high-dimensional feature selection and machine learning methods in early default prediction for consumer credit," 2025. doi: 10.22541/essoar.176126753.35589371/v1
15. 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
16. M. Yuan, W. Qin, J. Huang, and Z. Han, "A robotic digital construction workflow for puzzle-assembled freeform architectural components using castable sustainable materials," Available at SSRN 5452174, 2025. doi: 10.2139/ssrn.5433279
17. D. Clear, "Managing sudden phase transitions in complex adaptive systems: Lessons from the financial crisis (Doctoral dissertation, University of Glasgow)," 2017.
18. A. D'Agostino, and J. Cimadomo, "Combining time-variation and mixed-frequencies: An analysis of government spending multipliers in Italy," 2015. doi: 10.2139/ssrn.3144751
19. D. Campbell, C. K. Upadhyay, and S. Johnson, "A state-wise analysis," Power Engineering and Intelligent Systems: Proceedings of PEIS 2024, Volume 2, vol. 1247, p. 197, 2024.
20. H. Chen, J. Li, X. Ma, and Y. Mao, "Real-time response optimization in speech interaction: A mixed-signal processing solution incorporating C++ and DSPs," In 2025 7th International Conference on Artificial Intelligence Technologies and Applications (ICAITA), June, 2025, pp. 110-114. doi: 10.1109/icaita67588.2025.11137915
21. A. Macaulay, and W. Song, "Narrative-driven fluctuations in sentiment: Evidence linking traditional and social media (No. 2023-23)," Bank of Canada, 2023.
22. C. Wu, J. Zhu, and Y. Yao, "Identifying and optimizing performance bottlenecks of logging systems for augmented reality platforms," 2025. doi: 10.20944/preprints202509.0357.v1