Knowledge-based FIS and ANFIS models development and comparison for residential real estate valuation

0Citations
Citations of this article
7Readers
Mendeley users who have this article in their library.

Abstract

There has been an increasing concern on the development of alternative approaches to overcome the problems and deficiencies that occur during the application of real-estate valuation methods. This study was established to investigate the usability of the expert knowledge based fuzzy logic methodology in determining real-estates values. In addition, valuation with the Adaptive Neuro-Fuzzy Inference System (ANFIS) method provided model comparison. Samples were administered a questionnaire for the parameters planned for these models regarding the parameters that affect real estate values. To make value estimations for the Fuzzy Inference System (FIS) model by using the parameters obtained from the questionnaire analyses, the criteria that produced the best results were acquired from the various criteria alternatives. An algorithm was created and the valuation process for real estate was performed using the FIS in Konya/Turkey. As a result of poll studies the area, age, floor conditions, physical properties and location of the real-estate property were considered as the input variables and the market value as the output variable. The memberships were established with poll analysis and were rule based on expert knowledge. The model structure was formed by using the Mamdani structure in the MATLAB fuzzy toolbox. Model prediction performance was evaluated statistically with the Mean Absolute Percentage Error (MAPE) and a high accuracy of the model results to the market values indicated the reliability of the established model for residential real-estate valuation.

Cite

CITATION STYLE

APA

Yalpir, S., & Ozkan, G. (2018). Knowledge-based FIS and ANFIS models development and comparison for residential real estate valuation. International Journal of Strategic Property Management, 22(2), 110–118. https://doi.org/10.3846/ijspm.2018.442

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free