The accurate prediction of house prices has important implications for the real estate industry, investors, and policymakers. In this study, we aimed to compare the performance of various regression models, including basic and advanced techniques, in predicting house prices using a public dataset containing 79 features. Our analysis included extensive feature engineering and data preprocessing to ensure the best possible performance of each model. Our findings suggest that advanced models, such as Bayesian regression and kernel regression having mean cross_val_score 0.9046 and 0.9058 respectively, outperformed basic models, such as multiple linear regression and polynomial regression. We also identified the importance of addressing issues such as multi-collinearity and outliers in the data to ensure the accuracy of the models. Our study contributes to the development of more precise and reliable methods for predicting house prices, providing insights into the strengths and limitations of different regression models. The implications of our work extend to the real estate industry, policymakers, and investors who rely on accurate real estate valuations for informed decision-making. Our results can be used to guide the selection of appropriate regression models and improve the accuracy of house price predictions.