The world’s growing population needs adequate and safe homes. In order to provide and increase the number and quality of housing projects, new alternative methods need to be investigated. In this paper, the use of artificial intelligence in decision making for housing projects will be presented. The artificial intelligence tool to be utilized will be artificial neural network algorithms. The complexity of issues related to planning and design of housing projects will be simplified into social, economic, engineering, environment and safety issues. In the artificial neural network algorithm, the parameters including population, environment, distance from hospitals, distance from schools, seismicity level of district of project, climate, topography, distance from highways, financial criteria are used as input parameters. The housing project efficiency is determined by the output parameter of the algorithm. Different housing project areas’ data are used for training and testing the artificial intelligence model. Based on the results of the training phase, a forecasting study is presented for a specific area in Turkey. In order to reach the best results, various configurations and architectures are trained. The success rate of the model is measured by r2, a statistical indicator applied to the analysis. The best configurations, architectures, and error graphs are presented. Advantages of this innovative artificial intelligence approach are that; in the future, it can be utilized as a forecasting tool of efficiency of housing projects. Copyright © 2012 IAHS.
