Smart Housing Forecast: Leveraging AI Models for Predictive Pricing and Recommendations

People are careful when they are trying to buy a new house with their budgets and market strategies. This study explores the development of a Smart Housing Forecast with use a powerful machine learning models like XG Boost Regression, a powerful gradient boosting is used to enabling highly accurate pricing forecasting and for property recommendation a cosine similarity-based approach with give each buyer need which is suggested by needs. It is seen that not only buyers face problem while buying property but also seller face problem selling property so we use a analysis modules for them to understand for what price to sell and buy property by use graph like scatter plot which to helping buyers and sellers make well-informed selections, these predictive models allow real estate brokers to suggest properties in a more personalised way. A smart housing forecasting project supports SDG 11 by promoting sustainable urban development. It ensures economic feasibility, equitable access (SDG 10), ethical data practices (SDG 16), and health-focused recommendations (SDG 3). These efforts contribute to creating inclusive, safe communities, fostering resilient and sustainable cities in line with global goals.