Comparing three machine learning algorithms in the task of appraising commercial real estate

Sammanfattning: In a unique opportunity to examine rare appraisal data from the commercial real estate sector, the accuracy of three machine learning algorithms is compared in the task of appraising commercial real estate. The algorithms; random forests, support vector regression and artificial neural networks, are tested in research about residential real estate, but the area of commercial real estate has remained relatively unexplored due to corporate secrecy. The mean absolute percentage error of the trained models range from 44% to 24% and is held as a baseline. The best performing baseline model, Random forests, was then made more sophisticated in order to evaluate how much performance could increase. It was found that the introduction of Gradient boosting reduced the aforementioned error from 24% to 20%. In comparison, the average human expert appraiser performs at an average error of 12%. The conclusion is that more work is needed in order to compete with human expert appraisers - and that this is a feasible task considering some of the inherent issues within the used data could be resolved with much manual labor.