This study offers a web application for stock prediction that uses machine learning algorithms to forecast market performance and analyse the sentiment of financial news. LSTM, lexicon-based analysis, and vector-based machine learning approaches are employed. for stock forecasting and sentiment analysis. The sentiment analysis system classifies news headlines as either positive or negative with an accuracy rate of 86%. The mean absolute error of the stock prediction model\'s stock performance estimation is 3.4 percent. The total accuracy of both models in predicting stock performance is 83%. The results indicate the system\'s potential for use in the stock market by offering crucial insights into machine learning algorithms for sentiment analysis using financial news headlines and stock data prediction.
Introduction
This research explores the integration of sentiment analysis of financial news headlines with machine learning models to predict stock market trends. Given the complexity and volatility of stock markets, traditional analysis methods can be time-consuming and may not capture the nuanced impacts of news events. By leveraging sentiment analysis, investors can gain insights into market sentiment and make more informed decisions.
Key Components:
Sentiment Analysis: Financial news headlines are analyzed to classify sentiments as positive, negative, or neutral. This classification helps in understanding the market's emotional response to news events.
Machine Learning Models: Models such as Long Short-Term Memory (LSTM) networks are employed to predict stock price movements based on historical data and sentiment scores. These models can capture complex patterns and dependencies in time-series data.
Integration of News Sentiment: Incorporating sentiment scores from news headlines into predictive models enhances their accuracy. Studies have shown that models using sentiment analysis outperform those relying solely on historical stock data.
Applications:
Stock Price Prediction: By analyzing the sentiment of financial news, models can forecast short-term stock price movements, aiding investors in making timely decisions.
Market Trend Analysis: Sentiment analysis helps in identifying prevailing market sentiments, which can indicate potential market trends and shifts.
Conclusion
In this study, a completely functional system for sentiment analysis and stock data prediction using financial news headlines is presented. By combining techniques from financial analysis, natural language processing, and machine learning algorithms, the system shows promise in supporting users\' decision-making. The main takeaway from this study is sentiment analysis, which uses word embedding and vectorization to create sentiment from real-time data that is fed into the system. In order to help users estimate whether a financial news headline will be positive or negative, this algorithm extracts information from a variety of websites. Combining sentiment analysis with stock forecasting aids users in making informed financial decisions on equities. The study highlights how important sentiment analysis is to understanding actual data and how it affects stock performance. Despite these shortcomings, the system offers a solid foundation for further research and advancement in the field. Testing this approach for large stock exchange projects and investors on a large scale could lead to further improvements. Nonetheless, this financial technology system can offer crucial information on integrating data-driven strategies in the stock market.
References
[1] Wahyuningsih, T., Manongga, D., Sembiring, I., Wijono, S. (2024). Comparison of effectiveness of logistic regression, naive bayes, comparison of effectiveness of logistic regression, naive bayes. Procedia Computer Science, 234: 349-356. https://doi.org/10.1016/j.procs.2024.03.014
[2] Sarma, S.L.V.V.D., Sekhar, D.V., Murali, G. (2023). Neural network and sentimental model for prediction of stock trade value. Revue d\'Intelligence Artificielle, 37(2): 315-321. https://doi.org/10.18280/ria.370209
[3] Gupta, K., Jiwani, N., Afreen, N. (2023). A combined approach of sentimental analysis using machine learning techniques. Revue d\'Intelligence Artificielle, 37(1): 1-6. https://doi.org/10.18280/ria.370101
[4] Nemes, L., Kiss, A. (2021). Prediction of stock values changes using sentiment analysis of stock news headlines. Journal of Information and Telecommunication, 5(3): 375-394. https://doi.org/10.1080/24751839.2021.1874252
[5] Sidogi, T., Mbuvha, R., Marwala, T. (2021). Stock price prediction using sentiment analysis. In 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Melbourne, Australia, pp. 46-51. https://doi.org/10.1109/SMC52423.2021.9659283
[6] Li, Q., Wang, T., Li, P., Liu, L., Gong, Q., Chen, Y. (2014). The effect of news and public mood on stock movements. Information Sciences, 278: 826-840. https://doi.org/10.1016/j.ins.2014.03.096
[7] Nguyen, T.H., Shirai, K., Velcin, J. (2015). Sentiment analysis on social media for stock movement prediction. Expert Systems with Applications, 42(24): 9603-9611. https://doi.org/10.1016/j.eswa.2015.07.052
[8] Crone, S.F., Koeppel, C. (2014). Predicting exchange rates with sentiment indicators: An empirical evaluation using text mining and multilayer perceptrons. In 2014 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr), London, UK, pp. 114-121. https://doi.org/10.1109/CIFEr.2014.6924062
[9] Li, X., Huang, X., Deng, X., Zhu, S. (2014). Enhancing quantitative intra-day stock return prediction by integrating both market news and stock prices information. Neurocomputing, 142: 228-238. https://doi.org/10.1016/j.neucom.2014.04.043
[10] Zuo, Y., Kita, E. (2012). Stock price forecast using Bayesian network. Expert Systems with Applications, 39(8): 6729-6737. https://doi.org/10.1016/j.eswa.2011.12.035
[11] Katayama, D., Tsuda, K. (2018). A method of measurement of the impact of Japanese news on stock market. Procedia Computer Science, 126: 1336-1343. https://doi.org/10.1016/j.procs.2018.08.084
[12] Sheta, A. (2006). Software effort estimation and stock market prediction using takagi-sugeno fuzzy models. In 2006 IEEE International Conference on Fuzzy Systems, Vancouver, BC, Canada, pp. 171-178. https://doi.org/10.1109/FUZZY.2006.1681711
[13] Ho, W.L., Tung, W.L., Quek, C. (2010). Brain-inspired evolving neuro-fuzzy system for financial forecasting and trading of the s&p500 index. In PRICAI 2010: Trends in Artificial Intelligence: 11th Pacific Rim International Conference on Artificial Intelligence, Daegu, Korea, pp. 601-607. https://doi.org/10.1007/978-3-642-15246-7_56
[14] Nagar, A., Hahsler, M. (2012). Using text and data mining techniques to extract stock market sentiment from live news streams. In International Conference on Computer Technology and Science (ICCTS 2012), IACSIT Press, Singapore.
[15] Su, C.L., Chen, C.J., Yang, S.M. (2010). A self-organized neuro-fuzzy system for stock market dynamics modeling and forecasting. In Proceedings of the 14th WSEAS international conference on Computers: part of the 14th WSEAS CSCC multiconference-Volume II, pp. 733-745.
[16] Zarandi, M.F., Rezaee, B., Turksen, I.B., Neshat, E. (2009). A type-2 fuzzy rule-based expert system model for stock price analysis. Expert systems with Applications, 36(1): 139-154. https://doi.org/10.1016/j.eswa.2007.09.034
[17] Sim, K., Gopalkrishnan, V., Phua, C., Cong, G. (2012). 3D subspace clustering for value investing. IEEE Intelligent Systems, 29(2): 52-59. https://doi.org/10.1109/MIS.2012.24
[18] Chowdhury, S.G., Routh, S., Chakrabarti, S. (2014). News analytics and sentiment analysis to predict stock price trends. International Journal of Computer Science and Information Technologies, 5(3): 3595-3604.
[19] Nalabala, D., Bhat, M.N. (2020). Predicting the E-commerce companies stock with the aid of web advertising via search engine and social media. Revue d\'Intelligence Artificielle, 34(1): 89-94. https://doi.org/10.18280/ria.340112
[20] Tudor, C. (2012). Active portfolio management on the Romanian stock market. 8th International Strategic Management Conference, Procedia - Social and Behavioral Sciences, 58: 543-551. https://doi.org/10.1016/j.sbspro.2012.09.1031
[21] Lenten, L., Crosby P., McKenzie J. (2019). Sentiment and bias in performance evaluation by impartial arbitrators. Economic Modelling, 76: 128-134. https://doi.org/10.1016/j.econmod.2018.07.026
[22] Venturini, A. (2022). Climate change, risk factors and stock returns: A review of the literature. International Review of Financial Analysis, 79: 101934. https://doi.org/10.1016/j.irfa.2021.101934.
[23] Nalabala, D., Nirupamabhat, M. (2020). An optimized machine learning model for stock trend anticipation. Ingénierie des Systèmes d’Information, 25(6): 783-792. https://doi.org/10.18280/isi.250608