STM Journals Peer-reviewed research from Consortium e-Learning Network

E-Commerce for Future & Trends Review Article

Stock Market Prediction Using Machine Learning: Techniques, Challenges, and Future Directions

  1. Nirav Shukla Chimanbhai Patel Institute of Computer Applications, Sardar Vallabhbhai Global University, Ahmedabad
  2. Vishal Dahiya Department of MCA, Chimanbhai Patel Institute of Computer Applications, Sardar Vallabhbhai Global University, Ahmedabad

Abstract

The continuous advancement of machine learning (ML) technologies has significantly transformed the field of financial forecasting, particularly in the area of stock market prediction. The ability to accurately forecast stock price movements and market trends plays a crucial role in supporting informed investment strategies and effective risk management. This paper provides a comprehensive review of recent developments in the application of ML techniques for predicting stock market behavior. It classifies the various ML approaches used in this domain and explores the growing importance of alternative data sources, such as financial news, social media sentiment, and market-related textual information, in enhancing prediction accuracy. In addition, the study presents a comparative assessment of different ML models based on their performance in real-world forecasting scenarios. It highlights several major challenges faced in stock market prediction, including the nonstationary nature of financial data, the risk of model overfitting, limited interpretability of complex algorithms, issues related to data reliability, and practical economic constraints. These factors often limit the effectiveness and applicability of ML models in financial decision-making. The paper concludes by outlining potential future research directions aimed at developing more reliable, interpretable, and economically practical ML models that can better support decision-making processes in the financial sector.

Keywords

References (10)

  1. Saberironaghi M, Ren J, Saberironaghi A. Stock Market Prediction Using Machine Learning and Deep Learning Techniques: A Review. AppliedMath. 2025;5(3):76. doi:10.3390/appliedmath5030076
  2. Janková Z. CRITICAL REVIEW OF TEXT MINING AND SENTIMENT ANALYSIS FOR STOCK MARKET PREDICTION. Journal of Business Economics and Management. 2023;24(1):177-198. doi:10.3846/jbem.2023.18805
  3. Gupta I, Madan TK, Singh S, Singh AK. HiSA-SMFM: Historical and sentiment analysis based stock market forecasting model. [Preprint]. 2022. arXiv:2203.08143. doi:10.48550/arXiv.2203.08143.
  4. Darapaneni N, Paduri AR, Sharma H, Manjrekar M, Hindlekar N, Bhagat P, et al. Stock price prediction using sentiment analysis and deep learning for Indian markets. [Preprint]. 2022;arXiv:2204.05783. doi:10.48550/arXiv.2204.05783.
  5. Chauhan A, Mayur P, Gokarakonda YS, Jamie P, Mehrotra N. Prediction of the Indian stock market using augmented financial intelligence ML. [Preprint]. 2024. arXiv:2407.02236. doi:10.48550/arXiv.2407.02236.
  6. Ong K, van der Heever W, Satapathy R, Cambria E, Mengaldo G. FinXABSA: Explainable Finance through Aspect-Based Sentiment Analysis. 2023 IEEE International Conference on Data Mining Workshops (ICDMW). 2023:773-782. doi:10.1109/icdmw60847.2023.00105
  7. Joseph TK, Verma V, Malik A, Alwakid GN, Hussain M. Forecasting Financial Markets: A Critical Analysis of Machine Learning and Social Sentiment Analysis. Lecture Notes in Networks and Systems. 2025:414-426. doi:10.1007/978-3-031-90998-6_38
  8. Joseph TK, Verma V, Malik A, Alwakid GN, Hussain M. Forecasting Financial Markets: A Critical Analysis of Machine Learning and Social Sentiment Analysis. Lecture Notes in Networks and Systems. 2025:414-426. doi:10.1007/978-3-031-90998-6_38
  9. More SV. Stock market prediction using financial news sentiments and technical indicator data with machine learning models and LIME for explainable insights [dissertation]. Dublin: National College of Ireland; 2024.
  10. Maddodi S, Kumar KN. Stock market forecasting: A review of the literature. Int J Inf Syst Comput Sci. 2021;5(3):141–151.
Support