When purchasing goods, buyers consistently prioritize the fairness of the price to make informed decisions, particularly for high-value items. This consideration becomes even more crucial in the real estate market, where verifying the fairness of a property's asking price through conventional methods can be challenging. This study addresses this issue by aiming to develop a functional predictive model that can estimate a property's intrinsic value using various machine learning techniques. By analyzing the California Census Data published by the US Census Bureau, this research investigates the potential for determining a property's intrinsic value based on readily available information about the block in which the property is situated. The study's objective is to create a model that provides accurate and reliable property valuations, helping buyers make more informed decisions and promoting transparency in the real estate market. This model leverages demographic, economic, and housing data from the census to predict property values, potentially transforming how properties are appraised and traded. By offering a method to verify asking prices, the research seeks to enhance fairness and efficiency in real estate transactions, providing a valuable tool for buyers, sellers, and real estate professionals alike.
Read full abstract