House Price Modeling in DKI Jakarta: A Web-Based Comparative Study of Spatial Models

A house is a fundamental need for individuals. House sellers can easily determine the market price of their property using the NJOP formula, which is used in the calculation of Land and Building Tax (PBB). However, for buyers, determining a fair market price for a house can be challenging. As a result, it is common for buyers to purchase a house at a price higher than its fair market value. Therefore, this study aims to determine the attributes of a house that affect the price of a house but also considering the spatial value of the location of the district of the house by comparing Spatial Autoregressive Model with Spatial Error Model. We concluded that the SEM model, characterized by the highest <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{R}^{2}$</tex> and the lowest AIC and BIC values, is identified as the best fit for the dataset. Furthermore, we embedded the house predicting models in a web application, making it easier for the public to determine the price of the house they want to purchase while also assisting property companies in planning future housing development strategies to generate maximum and sustainable profits.