A comparative performance analysis of linear regression techniques for predicting housing prices using the Boston Housing dataset. The algorithms evaluated include Ordinary Least Squares (OLS), Ridge Regression, Lasso Regression, and Elastic Net. These models were assessed using key performance metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-Squared (R2). A comprehensive methodology was followed, including data preprocessing, train-test splitting, and hyper parameter tuning for regularized models (Ridge, Lasso, and Elastic Net) using cross-validation. The results reveal that while OLS serves as a baseline, regularized techniques like Ridge and Elastic Net outperform in terms of generalization and robustness, especially in the presence of multicollinearity. Lasso's feature selection capability further highlights its utility in sparse settings. Elastic Net strikes a balance between Ridge and Lasso by combining their strengths. This analysis provides valuable insights into the suitability of various linear regression techniques for real-world predictive modeling tasks in housing markets. © 2025 Elsevier B.V., All rights reserved.