Home Price Prediction Using Machine Learning

Computer Science & Engineering

ABSTRACT The rapid expansion of the real estate industry, particularly in urban areas like Bangalore, has highlighted the need for efficient, accurate, and data-driven property valuation methods. Traditional techniques for estimating home prices often rely on manual assessments and subjective judgment, which can result in inconsistencies and lack of transparency. This paper introduces a machine learning-based predictive model designed to estimate home prices using key features such as total square footage, number of bedrooms (BHK), number of bathrooms, and geographic location. The model is trained using a structured dataset, where location is encoded using one-hot encoding to handle the city's diverse neighbourhoods, enabling the model to capture regional price variations effectively. The implementation includes a user-friendly web application built with Python and Flask, which allows users to input property details and receive instant price estimates. A database is integrated for user authentication and data storage. The model demonstrates strong predictive performance for properties within the Bangalore region, offering valuable support for buyers, sellers, and real estate agents. By automating the valuation process, this system enhances decision-making, promotes market transparency, and reduces the time and effort traditionally required for home price estimation.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.