Machine Learning Models for Predicting Stock Market Trends

Kannagi Rajkhowa, Yash Rawat

Abstract: The use of historical stock price data, which includes opening, high, low, closing prices, and trading volume, along with technical indicators like moving averages, Relative Strength Index, and Moving Average Convergence Divergence, aims to improve predictive performance and capture market momentum. Special consideration is given to examining how various models react to different levels of market volatility and the impact on their predictive accuracy during both stable and unstable market periods. As no single model reliably performs the best across all market conditions, conducting a comparative analysis is crucial for discovering an optimal strategy. Consequently, we will explore these different methods to determine the most effective stock price prediction technique based on performance metrics such as Mean Absolute Error, Root Mean Square Error, and Mean Absolute Percentage Error, along with robustness and computational efficiency. The results of this research are intended to add to the expanding field of financial prediction by offering a structured comparison of prediction models tailored to the Indian financial market.

Keywords: Stock Market, Finance, Machine Learning, Financial Analytics, Deep learning

How to Cite?: Kannagi Rajkhowa, Yash Rawat, "Machine Learning Models for Predicting Stock Market Trends", Volume 15 Issue 1, January 2026, International Journal of Science and Research (IJSR), Pages: 590-594, https://www.ijsr.net/getabstract.php?paperid=SR26108235429, DOI: https://dx.doi.org/10.21275/SR26108235429