House Price Prediction Model Selection Based on Lorenz and Concentration Curves: Empirical Evidence from Tehran House Market

This study provides a selection of the house price prediction model for the Tehran city based on the area between the Lorenz curve (LC) and the concentration curve (CC) of the forecast price using ۲۰۶,۵۵۶ observed transaction data from March ۲۱, ۲۰۱۸, to February ۱۹, ۲۰۲۱. Several different methods such as generalized linear models (GLM) and recursive partitioning and regression trees (RPART), random forests (RF) regression models, and neural network (NN) models for predicting housing prices. We used ۹۰% of all randomly selected data samples to estimate the parameters of pricing models and ۱۰% of the remaining data sets to test the accuracy of the prediction. The results showed that the area between the LC and CC curves (known as the ABC criterion) of reals and forecast prices in the test data sample of the random forest regression model was less than that of other models examined. The comparison of the calculated ABC criteria leads us to conclude that the nonlinear regression, like the RF regression model, provides an accurate prediction of housing prices in Tehran City.

کلیدواژه ها:

ABC Criteria ، City of Tehran ، Concentration Curves ، House Features ، Housing price ، Model Selection Metrics ، Price Prediction Models