Optimizing House Price Prediction: Comparative Analysis of Machine Learning Techniques

This research presents a comparative analysis of machine learning models for house price prediction across four distinct metropolitan areas: Pune, Bangalore, Mumbai, and Delhi. Leveraging historical data encompassing multidimensional attributes such as location, size, and amenities, we systematically assess the performance of diverse models, including Linear Regression, Decision Regression Tree, Random Forest, K-Nearest Neighbors (KNN), Decision Tree Classifier, and Gaussian Naïve Bayes. Through rigorous examination, we establish the Decision Regression Tree model as the optimal choice, demonstrating the highest average accuracy score of 96.27%. This model's capacity to capture intricate non-linear relationships within the dataset contributes to enhanced predictive efficacy, while its interpretability facilitates stakeholders' comprehension of underlying price determinants. By shedding light on model performance variations across different urban landscapes, this research furnishes valuable insights for informed decision-making in house price prediction within diverse real estate markets.