Building Logistics Cost Forecast Based on High Speed and Precise Genetic Algorithm Neural Network

The building logistics cost forecasting was a complicated nonlinear problem, due to the factors that influence building logistics cost are anfratuous, and it was difficult to describe it by traditional methods. So a modeling and forecasting method of building logistics cost based on high speed and precise genetic algorithm neural network is presented in this paper. The high speed and precise genetic algorithm neural network is combined the adaptive and floating-point code genetic algorithm with BP network which has higher accuracy and faster convergence speed. We constructed the network structure, and discussed and analyzed the effect factor of building logistics cost. With the ability of strong self-learning and faster convergence of high speed and precise genetic algorithm neural network, the modeling and forecasting method can truly forecast the building logistics cost by learning the index information. The actual forecasting results show that this method is feasible and effective. There are many ways to forecast the logistics, such as moving average method, exponential smoothing method, time series decomposition method, regression model method etc. These traditional methods are required to establish a clear functional relation with the forecasted goal, but the logistics system is always an open complex systems. There are a number of factors including both qualitative factors and quantitative indicators impact of the changes in the demand. In addition, the development of the logistics is always presented in a general non-linear and random state, and it is closely related to the level of economic development of the city, the government policies and other factors etc. These factors are not only difficult to describe quantitatively, but also difficult to establish the certain functional relation with the forecasted goal (2)-(3). So, it is not appropriate to use the aforementioned methods. The BP network based on gradient descend is a new