Abstract
In urban planning, housing evaluation of residential areas plays a critical role in promoting economic efficiency. This study produced an evolutionary-based map through the combination of hybrid Multicriteria Decision Making (MCDM) and Geographical Information System (GIS) by assessing suitability of housing location. Suitable locations were modelled and determined with the present study from very low suitability to very high suitability. In the first stage, Fuzzy DEMATEL (the Decision Making Trial and Evaluation Laboratory) and Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) under fuzzy conditions as a subjective and an objective (model-based) technique, respectively, were employed to find the weights of criteria which are critical part of decision making. In the second stage, housing evaluation map for these two approaches was drawn and their performances were classified and measured with WLC (Weighted Linear Combination) method. 29 criteria determined were prioritized as per judgment of urban planning and real estate experts for Fuzzy DEMATEL and CMA-ES. After having been coded to MATLAB for obtaining optimum weights in CMA-ES, all collected data for 160 houses were mapped as vectorial (positional) and transformed to raster (pixel) data by getting entered in ArcGIS 10.4 software. We achieved CMA-ES-WLC maximization values for 104 alternatives with (positive value) 65% performance, but we obtained FDEMATEL-WLC maximization values for 56 alternatives with (negative value) 35% performance. WLC values calculated with CMA-ES and FDEMATEL weights allowed us to conclude that the houses with the highest suitability in terms of investment are in Alpaslan, Köşk, and Melikgazi streets. The result shows that the methodology used in the application of this study performed in Turkey is an important and powerful technology in providing decision support for spatial planning.
Highlights
As urban population living in cities increases rapidly, it is crucial to preserve environmental values and improve quality of urban service and quality of life
The purpose of the comparison for the MCDA methods is to demonstrate the feasibility of the model-based objective approaches and which MCDA methods will be more suitable in selection and evaluation problems
The criteria weights obtained from Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) and the FDEMATEL algorithms were processed manually in ArcGIS using WLC method
Summary
As urban population living in cities increases rapidly, it is crucial to preserve environmental values and improve quality of urban service and quality of life. Housing problem (especially, for low income families) has not been fully resolved in both developed and developing countries from past to present [14] In countries such as Turkey where housing is seen as a guarantee, demand for investment by high income group is very important. Our study focuses on selection problem of best suitable among existing ones for sale with the help of housing suitability evaluation whenever a customer wants to buy a house depending on 29 criteria which are related to distance, building, and surrounding properties among others To solve this problem MCDM and Evolutionary Algorithm (EA) approaches can be considered with weighting of criteria to either single or multiple sets of objectives [20]. Many studies have used the MCDM techniques like ordered weighted averaging (OWA) [23], analytical hierarchy/network [24] process, ELECTRE (elimination and choice expressing reality) [25], PROMETHEE (the preference ranking organization method for enrichment of evaluations) [26], EA [27], Combined Decision Making Trial and Evaluation Laboratory (DEMATEL), the Analytic
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
