Analytical hierarchy process judgement matrix remodeling basing on Artificial Neural Network

The Analytical Hierarchy Process (AHP) has been widely used in the field of decision making and data analysis, but the consistency of the judge matrix severely restricts the application effect of this method. A three-layer BP neural network structure is built basing on the self-learning ability of the Artificial Neural Network in this paper. The neural network constantly optimize the weight and bias between layers through the learning of judge matrices with different level of consistency and then conduct the matrix reconstruction of incomplete matrices with the help of the trained BP neural network. Simulation results show that the trained neural network can fill the lost elements of the incomplete matrix without change many elements and effectively improve the consistency of judge matrices.