Research on the Prediction of Boston House Price Based on Linear Regression, Random Rorest, Xgboost and SVM Models

Abstract

Regression problems, which make up a significant portion of machine learning research, include the Boston housing price forecast problem. Regression problems are a subset of artificial intelligence. Regression problem-solving algorithms that are more frequently used four different machine learning models—the linear regression model, the Random Forest model based on an integrated learning technique, the XGBoost model, and the SVM model—are utilized for training and testing in this study. These models were chosen based on the real-world Boston house price prediction problem. From various angles, the effectiveness of the various algorithmic models on the regression problem of house price prediction was evaluated, and it was determined that among the many algorithmic models. For this problem, the best model is XGBoost Regression and the worst model was the SVM model. The most typical benefit of the XGBoost model is that It can capture complex non-linear relationships between variables.The disadvantage of the SVM model is its computational complexity.