关键词: 自适应神经模糊推理系统, k近邻, 房产评估, 地理位置

Abstract: The assessment of real estates is a complicated process in which there are some problems in the definition of neighbor. An adaptive neuro-fuzzy inference system added the k-nearest neighbors approach is used in the assessment of residential properties. By defining different k-nearest neighbors including all variables, partial variables, location, location and time, the average neighbor price of every real estate can be computed, then it is added into the input variables of the model. The simulation results show that the model using k-nearest neighbors with a location or with a location and time estimates the prices of properties more accurately.

Key words: Adaptive Neuro-Fuzzy Inference System（ANFIS）, k-nearest neighbor, real estate assessment, location