A commercial real estate price evaluation model based on GT-BCPSO-BP neural network

Aimed at coping with the complexity of commercial real estate price evaluation, the advantages of grey correlation theory, bacterial chemotaxis particle swarm algorithm and BP neural network are integrated to firstly put forward a novel model of commercial real estate cost evaluation. First, grey correlation theory was used to reduce the factors affecting commercial real estate price and optimise input variables of BP neural network. Then, the bacterial chemotaxis particle swarm algorithm with constriction factors is adopted to optimise the initial weights and thresholds. Through this method, BP neural network can be used to solve nonlinear problems and to improve the rate of convergence and the ability to search global optimum. An engineering project in the city of Hunan is selected to make empirical analysis. It shows that this novel model enjoys a high practical value as it can be applied to make scientific evaluation of commercial real estate price evaluation.