Machine Learning Empowered House Price Prediction Model

People are vigilant about buying a new house or plot where they are enthusiastic to live. They are likewise capricious in the land because of the inclusion of a non-regularized real estate market in urban areas. Hence, the expected price should be assessed in the existing city context. This study discusses Extreme Gradient Boosting, Gradient Boosting Regression, Random Forest Regression, Light Gradient Boosting Machine Regression, and Support Vector Regression to determine plot prices for housing societies. This system will be helpful to people to reach their buying choice quickly with their budget limitations and financial requirements. This research has also used Grid Search CV, Random Search, and Particle Swarm Optimization. Random forests show the minimum error rate by using PSO. This proposed model shows better performance by using Particle Swarm Optimization (PSO) as compared to a Light Gradient Boosting Machine Regression approach.