• Surbhi Sahu
• Anurag Jain
• Rajneesh Pachouri

Accurate prediction of stock market trends is an essential component of financial forecasting, necessitating the use of robust methodologies to navigate the complexities inherent in dynamic market behaviors. This research undertakes a comparative analysis of various machine learning models, including Support Vector Regression (SVR), Linear Regression, Random Forest, K-Nearest Neighbors (KNN), Decision Tree, and Elastic Net, aimed at forecasting stock market trends for three NIFTY indices: Financial Services, Information Technology, and Metals. The assessment utilizes Mean Squared Error (MSE) as a metric, alongside the precision of predicting opening stock values. The findings reveal that the Decision Tree model consistently yields the lowest MSE across all examined indices, signifying its superior predictive capabilities. The Random Forest model also demonstrates competitive performance, particularly within the NIFTY Financial Services and NIFTY Metals indices, providing reliable predictions characterized by low MSE. Conversely, SVR models show elevated MSE values, indicating their limited efficacy in this particular analysis. This study underscores the importance of model selection in financial forecasting and highlights the potential of tree-based methodologies in effectively capturing nonlinear relationships present in stock market data. This research enhances the field of predictive analytics within financial markets by identifying effective machine learning models for stock trend forecasting. Future investigations may focus on the integration of real-time data, optimization of hyperparameters, and the expansion of the analysis to encompass global markets, thereby improving the robustness and applicability of these predictive models.

Stock Market Prediction, NIFTY Indices, Machine Learning, Decision Tree, Random Forest, Mean Squared Error.

"Comparative Analysis of Machine Learning Models for Predicting Stock Market Trends in NIFTY Indices", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 1, page no.f135-f140, January-2025, Available :http://www.jetir.org/papers/JETIR2501512.pdf

"Comparative Analysis of Machine Learning Models for Predicting Stock Market Trends in NIFTY Indices", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 1, page no. ppf135-f140, January-2025, Available at : http://www.jetir.org/papers/JETIR2501512.pdf