• Mrs. Shalini Jain
• Mr. Sarvesh Singh Rai,
• Dr. Navdeep Kaur Saluja

This research presents a comprehensive comparative analysis of Machine Learning (ML) and Deep Learning (DL) algorithms for predicting stock market trends across NIFTY indices. The study evaluates multiple algorithms—including Decision Trees, Random Forests, Support Vector Machines, K-Nearest Neighbors, Linear Regression, and advanced neural network architectures—using both continuous data (stock prices, volumes, technical indicators) and binary data (directional movements). Performance evaluation employs Mean Squared Error (MSE) and prediction accuracy metrics. Results demonstrate that while tree-based ensemble methods (Random Forests, Decision Trees) achieve superior performance on NIFTY Financial Services and NIFTY Metals indices with MSE values as low as 4,100.98 and 544.70 respectively, deep learning approaches (LSTM, GRU) excel in capturing temporal dependencies for longer-horizon predictions. This research contributes to financial forecasting literature by providing practitioners with evidence-based guidance for algorithm selection based on index characteristics and data representation methods.

Stock market prediction, NIFTY indices, machine learning, deep learning, Random Forest, LSTM, comparative analysis, financial forecastin.

"A Comparative Predictive Analysis of Stock Market Trends Using Machine Learning Models", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 1, page no.e548-e558, January-2026, Available :http://www.jetir.org/papers/JETIR2601478.pdf

"A Comparative Predictive Analysis of Stock Market Trends Using Machine Learning Models", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 1, page no. ppe548-e558, January-2026, Available at : http://www.jetir.org/papers/JETIR2601478.pdf