House Price Prediction System Based on Ensemble Learning
A course project in CS182 Introduction to Machine Learning
Abstract
In this project, we propose a novel system for predicting house prices using ensemble learning techniques. Leveraging the dataset from the Kaggle competition “House Prices - Advanced Regression Techniques”, we aim to enhance the accuracy and robustness of price predictions by combining multiple models. Our approach integrates various machine learning algorithms, including linear regression, random forest, and gradient boosting, to capture different aspects of the data. By optimizing the ensemble model, we achieve superior performance compared to individual models. This report details the data preprocessing steps, model selection, and the ensemble strategy employed. The results demonstrate that our ensemble learning approach significantly improves predictive accuracy comparing with single model.