Investment analysis of real estate by using radial basis probabilistic neural networks

intelligent Decision Analysis System (IDAS) for real estate investment involves a great deal of factors, such as market of house property, urban construction, construction material, etc. In this paper, we consider the main factors that affect the selling price of the real estate products, and propose a selling price prediction model by using a radial basis probabilistic neural network (RBPNN). The RBPNN consists of four layers: one input layer, two hidden layers, and one output layer. Input layer has four nodes, which are four main factors: the content rate, the environment landscape, the public traffic condition, and the location of the real estate. The output is the selling price, which has 10 nodes corresponding to the 10 classes of the selling price. We totally collect 180 samples of living areas in Shanghai, 150 of which are used as the training data, and 30 of which are used to examine the model. The experiment results are fitted to the practical instances, and verify the feasibility of the RBPNN-based selling price prediction model.