Spatial Modeling for Predicting the Default of Commercial Real Estate

Authors: Jingyi Xiao*, University of California, Santa Barbara, Jake Carr, Moody’s Analytics
Topics: Spatial Analysis & Modeling, Economic Geography, Geographic Information Science and Systems
Keywords: Spatial analysis, Spatial modeling, GIS
Session Type: Paper
Day: 4/4/2019
Start / End Time: 9:55 AM / 11:35 AM
Room: Roosevelt 0, Marriott, Exhibition Level
Presentation File: No File Uploaded


“Location, Location, Location” are the three most important factors in determining the value of a property. Spatial modeling and analysis have been consequently used in real estate studies for a long time. The majority of studies on real estate focus on predicting property prices, which is a continuous variable in statistical modeling. In this study, we propose an alternative spatial modeling method to predict the binary outcome of default status. The presentation will discuss the model specification, the estimation method, and the model’s performance and evaluation.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login