Predicting Rental Prices in India: A Machine Learning Approach with Hyperparameter Optimization

This paper presents a comprehensive analysis and predictive modeling approach for rental prices in India. Utilizing a dataset of house rents from Kaggle, this study employs a range of machine learning algorithms to analyze and forecast rental prices. The methodology begins with establishing baselines using simple regression techniques. It then advances to more sophisticated models, including Gradient Boosting (GB) and Extreme GB (XGBoost), to enhance prediction accuracy. Hyperparameter tuning is conducted using the OPTUNA framework to identify the most effective algorithm. In cases of potential overfitting, the study shifts to ensemble methods, such as voting and bagging models, to improve robustness and generalizability. The paper aims to cover exploratory data analysis, data preprocessing, model training, and performance evaluation. By systematically comparing different algorithms and optimizing their parameters, this research provides a detailed framework for predicting rental prices with greater accuracy. The findings offer valuable insights for making informed decisions in real estate investments and rental management in India.