Regression, a cornerstone of machine learning since its inception, has continually played a pivotal role in solving a wide array of problems. Predating the advent of advanced neural networks and deep learning models which are mainly predominant today, regression methods have consistently demonstrated their efficacy. This study delves into an in-depth analysis of types various regression models, explores diverse feature engineering techniques, and evaluates their respective impacts on predictive performance. The study aims to provide a comprehensive understanding of regression’s applicability and utility by applying these methods to a dataset of stock prices of various companies in a particular sector. By examining the performance of these different regression models and investigating various feature engineering strategies, this research offers valuable insights into the practical aspects of regression in a real-world financial context. The results obtained through these analyses shed light on the strengths and weaknesses of different regression approaches, enabling data scientists and machine learning practitioners to make informed choices when addressing financial forecasting and related challenges. In summary, this work contributes to the ongoing discourse on the relevance and effectiveness of regression in contemporary machine learning, with a specific focus on its application to stock price prediction.