• Abheesh Puthukkudy
• Chethan T S

The value of a company's stock, which can increase along with the cost of an individual share, is the best measure of its success. Understanding the dynamics of stock market trends, seasonality, and noise is crucial for investors to make informed decisions. In this study, we aim to compare the performance of five different stocks using three distinct analysis methods: Linear Regression, Grid Search CV, and Extreme Learning Machine (ELM). The volatility of stock prices poses a challenge for predicting future values, prompting the exploration of machine learning algorithms as potential solutions. Leveraging Python and time series analysis, we are developing a stock price prediction platform based on historical data. Our primary objective is to enhance the precision of stock price forecasts by integrating linear regression models with time series analysis, considering temporal dynamics. By adjusting the dataset used for training linear regression models, we aim to improve accuracy. Ultimately, our research aims to demonstrate the efficacy of combining linear regression and time series analysis as the most efficient approach for stock market forecasting.

"Unlocking Stock Market Trends: Leveraging Machine Learning and Time Series Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.g522-g533, May-2024, Available :http://www.jetir.org/papers/JETIR2405663.pdf

"Unlocking Stock Market Trends: Leveraging Machine Learning and Time Series Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppg522-g533, May-2024, Available at : http://www.jetir.org/papers/JETIR2405663.pdf