Comparison and Analysis of Boston Housing Price Predictions Using Different Machine Learning Methods

In the contemporary real estate market, housing prices are fiercely competitive and influenced by various factors, such as the criminal activities existing in the community and the quality of the surrounding environment. However, inaccuracies in predicting house prices often lead to problems such as excessively high prices. The application of corresponding machine learning models plays a significant role in improving predictive accuracy in this domain. This study compares multiple models, including Ordinary Least Squares (OLS), Ridge regression, Lasso, Elastic Net, Random Forest, and Multilayer Perceptron (MLP), using a real-world housing price dataset. Model performance is evaluated through the accuracy, R², RMSE, and MSE. The final results indicate that the Random Forest outperforms the other methods, achieving the highest predictive accuracy, while Ordinary Least Squares produces the lowest accuracy. Additionally, the study examines the applicability of these techniques across various scenarios and their potential to enhance the accuracy of housing price predictions.