Predicting New York Housing Prices: A Machine Learning Approach Incorporating School, Living facilities and Real Estate Market Factors

Abstract

This study aims to predict housing prices in New York by utilizing machine learning methods that incorporate factors such as schools, living facilities, and the real estate market. This paper collected extensive data, including metrics on school quality, assessments of living facility convenience, and real estate market data. Employing a regression-based machine learning algorithm, the study incorporated these factors into a predictive model. Through training and testing the model, this study discovered that school quantity and the convenience of living facilities significantly impact housing prices. The predictive model demonstrated good accuracy and predictive capability on the test set, validating the effectiveness of this approach. The findings of this study provide valuable insights for real estate market participants, policymakers, and investors to better understand and forecast housing price trends in New York.