House Price Prediction
Regression-based machine learning project for predicting house prices from structured property data. The project compares multiple models, applies preprocessing and feature engineering, and evaluates performance using standard regression metrics.
Tech Stack
Dataset
The dataset contains multiple features of houses, which serve as predictors for estimating house prices. The dataset is preprocessed to handle missing values, normalize numerical variables, and encode categorical features where necessary.
Machine Learning Models Tested
-
Linear Regression
-
Decision Tree Regressor
-
Random Forest Regressor
-
Gradient Boosting Regressor
-
Support Vector Regressor (SVR)
Final Model Performance Metrics
The best-performing model achieved the following metrics:
-
Mean Absolute Error (MAE): 0.0280
-
Mean Squared Error (MSE): 0.0024
-
Root Mean Squared Error (RMSE): 0.0489
-
R-squared (R2): 0.5388
-
Adjusted R-squared: 0.2377