Integrating Random Forest and XGBoost For Accurate House Rent Prediction
Harsh Vardhan Singh, Santosh Kumar Srivastava, Nishant Kumar Pandey, Nitesh Kumar · 2025
Predicting house rents accurately is essential for tenants, landlords, and investors to make informed decisions in the real estate market, particularly given the rising trends in rental prices. This study employs machine learning techniques, including Random Forest and XGBoost, to predict rental values based on factors such as location, area, square footage, rent, and house size. The dataset was preprocessed using Python libraries such as NumPy, pandas, and scikit-learn, with steps including data cleaning, normalization, and feature engineering. Features such as house age, floor details, and distance from city centers were derived to enhance model performance. Evaluation metrics like Root Mean Squared Error (RMSE) were used to measure accuracy. The Random Forest algorithm achieved superior results with its robustness against overfitting and its ability to model complex relationships. XGBoost, with its scalability and speed, also delivered competitive performance. The ensemble approach of these models further improved prediction accuracy by leveraging their individual strengths.The developed system achieved exceptional performance metrics, including a Mean Squared Error (MSE) of 0.0001, Root Mean Squared Error (RMSE) of 0.01, Mean Absolute Error (MAE) of 0.01, and an R-squared value (R2) of 0.9998, indicating high accuracy and robustness in predicting house prices This research highlights the utility of advanced machine learning algorithms and proper preprocessing techniques in real estate analytics.