Estimation of real estate asset pricing models

Fecha

2016

Autores

Arias Arbeláez, Felipe Alonso

Título de la revista

ISSN de la revista

Título del volumen

Editor

Universidad EAFIT

Resumen

In this project we aim to develop 4 different methods in order to estimate the real market price of 380 properties owned by Midtown Realty Group in Miami, Florida -- We used the ordinary least squares, generalized method of moments, artificial neural networks and fuzzy inference systems -- The comparison between the 4 models was made using the root mean squared errors (RMSE) with an interesting result showing that the best method to estimate housing price given our data set is the artificial neural network using the correct network architecture -- Some further work is proposed in order to make more comparison between the models and dene the best model for housing price

Descripción

Citación