Residential property price forecasting model for central Pangasinan

This quantitative-experimental study aims to develop a residential property price forecasting model for the fourteen municipalities and cities of central Pangasinan, Philippines. Employing supervised learning classification algorithms (linear regression and decision tree), the model predicts whether the value of real properties will increase or decrease in the future. Additionally, classic statistical forecasting techniques (straight line, moving average, simple linear regression, and multiple linear regression) are utilized to predict the rate of increase or decrease, with a margin of error of +/- 5%. The study sources data from the Residential Real Estate Price Index (RREPI) of the Banko Sentral ng Pilipinas (BSP) from 2016 to 2021, Zonal Valuations (ZV) from the Bureau of Internal Revenue (BIR) from 1990 to 2023, and the Housing Cost Construction Index (HCCI) from the Philippine Statistics Authority (PSA) from 2006 to 2021, following an 80:20 training-testing data split ratio. The resulting model, employing the RandomForest algorithm, exhibits a significant accuracy rate of 93% and a precision rate of 93%. Comparative analysis demonstrates that machine learning-based algorithms, particularly Random Forest, outperform classic statistical forecasting techniques such as multiple linear regression, attaining an average prediction distance point of 4.32% versus 12.46%. The study's findings carry profound implications for resilient planning and disaster mitigation in Central Pangasinan. By identifying areas with predicted property value increases, the model empowers local governments and community organizations to prioritize resilient planning efforts. This includes the strategic implementation of disaster mitigation strategies, such as flood control measures and coastal protection, in regions projected to experience property value growth.