Everyone can now find an affordable residence near nature that features every modern convenience. For the advantage of the public, efforts to construct new forms of affordable housing have been hampered by rising housing costs. It may be more informative and appealing to prospective buyers if you provide a range of property value losses instead of a single estimate. Approximating costs may prove challenging due to the inherent complexities involved in product categorization. Researchers often employ the House Price Index (HPI) inquiry method to predict future housing price fluctuations accurately. This involves calculating the average price difference among numerous acquisitions or refinancing agreements involving identical properties. Several variables, including population density and geographic location, influence real estate price trends, further complicating the situation. To estimate and recommend property prices in this study, four distinct methods were implemented: a gradient boost regressor, a decision tree, a linear regression, and a random forest regressor. You should be capable of constructing a dependable machine-learning model for applications such as data classification and predictive analytics if you adhere to these steps. We compared the predictive capabilities of the sources. Approximately 13,000 documents from the Bengaluru dataset are utilized in the investigation. The Gradient Boost Regressor can provide dependable real estate investment recommendations with a success rate of 99.94% due to the caliber of its output. The Gradient Boost Regressor was selected as the foundational model for assessing property values and providing recommendations due to its highest reliability among the alternatives.