A-share Trend Prediction Based on Machine Learning and Sentiment Analysis
DOI:
https://doi.org/10.61173/52jy4c52Keywords:
A-share market, machine learning, sentiment analysis, financial forecastingAbstract
This study addresses the predictive challenges in China’s A-share market, characterized by high retail investor participation and significant policy impacts. We introduce a novel predictive model that leverages both machine learning algorithms and sentiment analysis to forecast market trends. The research utilizes comprehensive datasets, including real-time A-share market data and sentiment-derived data from stock-related news, processed via advanced machine learning techniques like Random Forest and sentiment analysis tools. Our approach innovatively combines traditional technical indicators with sentiment scores to enhance the predictive accuracy of the model. The findings suggest that integrating sentiment analysis significantly improves the model’s performance, evidenced by enhanced prediction metrics such as Mean Absolute Error (MAE) and R-squared values, which compare favorably before and after incorporating sentiment data. This study not only contributes to the existing financial prediction literature by providing a hybrid methodological approach but also offers practical implications for investors and policymakers in navigating the volatile A-share market.
References
4. Conclusion 1)Antweiler, W., & Frank, M. Z. (2004). Is all that talk This paper delves into the prediction of A-share market just noise? The information content of internet stock mestrends using machine learning and sentiment analysis, sage boards. The Journal of Finance, 59(3), 1259-1294. enhancing predictive capabilities by combining traditional 2)Yong, W., Multi-mode Matching Identification Algotechnical analysis with advanced algorithms. It details the rithm for Short-term Stock Investment Forecasting[J]. entire workflow from data collection to model deploy- Computer Applications, 2014, 34(S2):180-183. ment, covering data preprocessing, feature engineering, 3)Xia, G., Research on Financial Market Trend Prediction model training, validation, and the final deployment and based on Machine Learning Algorithms[J]. Microcomputperformance monitoring. er Application, 2023, 39(02): 30-32+40. The research highlights the crucial role of data preprocess- 4)Bollen, J., Mao, H., & Zeng, X. (2011). Twitter mood ing in addressing missing values and outliers in financial predicts the stock market. Journal of Computational Scitime series. Feature engineering is enriched by incorpo- ence, 2(1), 1-8. rating technical indicators like RSI, EMA, and sentiment 5)Das, S. R., & Chen, M. Y. (2007). Yahoo! for Amazon: scores, creating a robust feature set that captures market Sentiment extraction from small talk on the web. Managetrends and emotions. The effectiveness of random forests ment Science, 53(9), 1375-1388. and gradient boosting trees in managing complex non-lin- 6)Guang, Liu., Research and Application of Stock Market ear relationships is confirmed, with performance metrics Prediction Model and Evaluation Method Based on Deep such as MSE, MAE, MAPE, and R² demonstrating the Learning [D]. Beijing University of Posts and Telecommodels’ accuracy and generalization capability. These munications, 2020. models provide reliable predictions that can guide investor 7)Ding, X., Zhang, Y., Liu, T., & Duan, J. (2015). Deep decisions in the A-share market. learning for event-driven stock prediction. In Proceedings The study concludes with the successful practical ap- of the 24th International Conference on Artificial Intelliplication of the model, bridging theory and practice for gence. AAAI Press, 2327-2333. operational use in trading systems. Looking forward, the 8)Engelberg, J., Sasseville, C., & Williams, J. (2012).
Market Madness? The Case of Mad Money. Management 16)Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015). Science, 58(2), 351-364. Predicting stock market index using fusion of machine 9)Fama, E. F. (1970). Efficient capital markets: A review learning techniques. Expert Systems with Applications, of theory and empirical work. The Journal of Finance, 42(4), 2162-2172. 25(2), 383-417. 17)Schumaker, R. P., & Chen, H. (2009). Textual analysis 10)Hagenau, M., Liebmann, M., & Neumann, D. (2013). of stock market prediction using breaking financial news: Automated news reading: Stock price prediction based on The AZFin text system. ACM Transactions on Informafinancial news using context-capturing features. Decision tion Systems, 27(2), 12. Support Systems, 55(3), 685-697. 18)Tetlock, P. C. (2007). Giving content to investor senti- 11)Hiransha, M., Gopalakrishnan, E. A., Menon, V. K., & ment: The role of media in the stock market. The Journal Soman, K. P. (2018). NSE Stock Market Prediction Using of Finance, 62(3), 1139-1168. Deep-Learning Models. Procedia Computer Science, 132, 19)Bar-Haim, R., Dinur, E., Feldman, R., Fresko, M., & 1351-1362. Goldstein, G. (2011). Identifying and following expert 12)Krauss, C., Do, X. A., & Huck, N. (2017). Deep neural investors in stock microblogs. In Proceedings of the Connetworks, gradient-boosted trees, random forests: Statisti- ference on Empirical Methods in Natural Language Procal arbitrage on the S&P 500. European Journal of Opera- cessing. 1310-1319. tional Research, 259(2), 689-702. 20)O’Hare, N., Lee, H., Cooray, S., Gruhl, D., & Nelson, 13)Li, X., Xie, H., Chen, L., Wang, J., & Deng, X. (2014). D. (2009). Detection and visualization of stock mentions News impact on stock price return via sentiment analysis. on Twitter. In IUI Workshops. Knowledge-Based Systems, 69, 14-23. 21)Si, J., Mukherjee, A., Liu, B., Li, Q., Li, H., & Deng, X. 14)Luss, R., & d’Aspremont, A. (2015). Predicting Ab- (2013). Exploiting topic based Twitter sentiment for stock normal Returns From News Using Text Classification. prediction. In Proceedings of the 51st Annual Meeting of Quantitative Finance, 15(6), 999-1012. the Association for Computational Linguistics. 24-29. 15)Nguyen, T. H., Shirai, K., & Velcin, J. (2015). Senti- 22)Zhang, W., & Skiena, S. (2010). Trading strategies to ment analysis on social media for stock movement pre- exploit blog and news sentiment. In Proceedings of the diction. Expert Systems with Applications, 42(24), 9603- Fourth International AAAI Conference on Weblogs and 9611. Social Media. 375-378.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
