A spatio-temporal, Gaussian process regression, real-estate price predictor

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Authors

Colleges, School and Institutes

External organisations

  • University of Warwick
  • Unit 46 Innovation Centre

Abstract

This paper introduces a novel four-stage methodology for real-estate valuation. This research shows that space, property, economic, neighbourhood and time features are all contributing factors in producing a house price predictor in which validation shows a 96.6% accuracy on Gaussian Process Regression beating regression-kriging, random forests and an M5P-decision-tree. The output is integrated into a commercial real estate decision engine.

Bibliographic note

Publisher Copyright: © 2016 ACM.

Details

Original languageEnglish
Title of host publication24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2016
EditorsMatthias Renz, Mohamed Ali, Shawn Newsam, Matthias Renz, Siva Ravada, Goce Trajcevski
Publication statusPublished - 31 Oct 2016
Event24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2016 - Burlingame, United States
Duration: 31 Oct 20163 Nov 2016

Publication series

NameGIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems

Conference

Conference24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2016
Country/TerritoryUnited States
CityBurlingame
Period31/10/163/11/16

Keywords

  • Gaussian Process Regression, Machine Learning, Real Estate Valuation, Space Time Cube, Universal Kriging