Ensemble Machine Learning Models Used for Forecasting in Rental Apartment Price Prediction of Metro City in India

In order to help stakeholders make well-informed real estate decisions, this study assesses two classes of machine learning algorithms to forecast rental home prices in India. The goal is to determine which models are the most accurate. The study examines a large dataset with characteristics including home type, size, location, and cost across major Indian cities using a quantitative research approach. A great deal of preprocessing was done, which included feature selection, dimensionality reduction, encoding categorical variables, and managing missing data.Its thorough assessment of a variety of machine learning models using a specially assembled dataset of rental properties in India is what makes the study distinctive. By concentrating exclusively on rental price prediction, this paper fills a need in the Indian market and adds to the body of previous material. The results show that the models' performance varied significantly, with the K-Neighbors Regressor surpassing the others by a little margin in terms of MAE. By demonstrating how machine learning may improve real estate market analysis and decision-making, this study makes a theoretical and practical contribution. A vital tool for investors, legislators, and prospective tenants, the comparison analysis provides insightful advice on how to choose models that strike a compromise between computational economy and prediction accuracy.