Boosted Tree Ensembles for Artificial Intelligence Based Automated Valuation Models (AI-AVM)

This paper develops an artificial intelligence based automated valuation model (AI-AVM) using the boosting tree ensemble technique to predict housing prices in Singapore. We use more than 300,000 private and public transactions Singapore for period from 1995 2017 training of AI-AVM models. The is best predictive that produce most robust accurate predictions compared decision multiple regression analysis (MRA) models explain 91.33% 94.28% price variances, keep mean absolute percentage errors at 8.55% 5.34% market market, respectively. When subject out-of-sample forecasting 2018 sale samples, prediction remain within a narrow range between 5% 9%.