Accuracy measurement of Random Forests and Linear Regression for mass appraisal models that estimate the prices of residential apartments in Nicosia, Cyprus

Thomas Dimopoulos,Nikolaos P Bakas,Diofantos Hadjimitsis,Hristos Tyralis

doi:10.5194/adgeo-45-377-2018

Thomas Dimopoulos, Nikolaos P Bakas + Show 2 more

Open Access

https://doi.org/10.5194/adgeo-45-377-2018

Copy DOI

Abstract

Abstract. The purpose of this article is to examine the prediction accuracy of the Random Forests, a machine learning method, when it is applied for residential mass appraisals in the city of Nicosia, Cyprus. The analysis is performed using transaction sales data from the Cyprus Department of Lands and Surveys, the Consumer Price Index of Cyprus from the Cyprus Statistical Service and the Central Bank of Cyprus' Residential Index (Price index for apartments). The Consumer Price Index and the price index for apartments record quarterly price changes, while the dependent variables for the computational models were the Declared and the Accepted Prices that were conditional on observed values of a variety of independent variables. The Random Forests method exhibited enhanced prediction accuracy, especially for the models that comprised of a sufficient number of independent variables, indicating the method as prominent, although it has not yet been utilized adequately for mass appraisals.

Highlights

Introduction and literature reviewThe Random Forests (RF) method is broadly used for predictive modeling as well as for data analysis and has been deemed significant in a wide variety of scientific thematic areas, such as Computer Science (Data Mining), Engineering, Medicine, Business etc
In 2001 the Random Forests was introduced by Breiman, in order to utilize a vast group of different decision trees creating a final result that is an average of the particular trees
This procedure resulted in high prediction performance, as well as the significance of each input variable, which is estimated automatically, regarding its contribution to the prediction errors

Summary

Introduction

Introduction and literature reviewThe Random Forests (RF) method is broadly used for predictive modeling as well as for data analysis and has been deemed significant in a wide variety of scientific thematic areas, such as Computer Science (Data Mining), Engineering, Medicine, Business etc. Decision trees are algorithmic structures that consist of nodes and branches. The model is trained to predict the desired output (dependent variable) with the minimum possible errors. In 2001 the Random Forests was introduced by Breiman, in order to utilize a vast group of different decision trees creating a final result that is an average of the particular trees. This procedure resulted in high prediction performance (accuracy), as well as the significance of each input variable, which is estimated automatically, regarding its contribution to the prediction errors

Objectives

Methods

Findings

Conclusion