Decoding ML Models Which Masters Stock Market Prediction

Author(s)	Ms. Priya Gupta, Dr. Kajol Verma, Dr. Rakesh Kumar, Dr. Sanil Kumar
Country	India
Abstract	Predicting the stock market has always been difficult because financial data is dynamic, volatile, and non-linear. Machine-learning (ML) models have become increasingly effective instruments for predicting stock prices and market trends as artificial intelligence has advanced. In this study, the predictive performance of three machine-learning models: SVM, LSTM, and MLP is assessed using stock price data from a subset of companies. The results show that no model performs better in every situation. Instead, the dataset's properties such as data patterns, volatility, and the volume of historical records have a significant impact on each model's accuracy and efficiency. MLP is good at capturing non-linear patterns in Mahindra and Mahindra, LSTM is efficient in the case of TATA Steel, and SVM shows good predictive ability in JSW. SVM and MLP both show satisfactory results in the case of Maruti Suzuki. As a result, all three models demonstrate effectiveness in various settings, highlighting the significance of data attributes when choosing a suitable machine-learning model for stock market prediction.
Keywords	Machine-learning, Stock Market, LSTM, SVM, MLP, Deep learning, Stock market prediction
Field	Mathematics > Economy / Commerce
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-04-06
DOI	https://doi.org/10.36948/ijfmr.2026.v08i02.72974

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research