• Gaurav D. Tivari
• Vishwa K. Patel
• Paras Narkhede
• Dr. Satvik Khara

Stock market forecasting remains a complex and highly pursued domain due to its potential for significant financial gains and economic insights. This paper presents a comprehensive evaluation of the precision of two prevalent predictive models: Regression and Long Short-Term Memory (LSTM) networks. Regression models, known for their simplicity and interpretability, and LSTM models, a type of recurrent neural network proficient in capturing temporal dependencies, are applied to historical stock market data to forecast future prices. The study compares the models' accuracy using key performance metrics such as Mean Squared Error (MSE) and Mean Absolute Error (MAE). Our findings indicate that while regression models offer a straightforward approach with satisfactory results, LSTM models significantly enhance predictive precision by effectively handling sequential data and capturing intricate market trends. The paper concludes with a discussion on the practical implications of these results for traders and financial analysts, emphasizing the strengths and limitations of each model in the context of stock market forecasting.

Stock Market Forecasting, Regression Models, LSTM Models, Time Series Analysis, Machine Learning, Financial Prediction, Deep Learning, Model Evaluation, Predictive Analytics, Market Trends

"Stock Market Forecasting: Evaluating the Precision of Regression and LSTM Models", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 7, page no.f115-f118, July-2024, Available :http://www.jetir.org/papers/JETIR2407518.pdf

"Stock Market Forecasting: Evaluating the Precision of Regression and LSTM Models", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 7, page no. ppf115-f118, July-2024, Available at : http://www.jetir.org/papers/JETIR2407518.pdf