With the first batch of 28 companies listed on the China's Growth Enterprise Market (GEM) on October 30, 2009, high issue prices, high P/E and high over-raising capital, known as "Tri-highs" phenomena, have received intensive attention and suspicions from the very beginning of the GEM's establishment in China. The IPO pricing efficiency become the subject of concern again. In view of the existing problems of IPO pricing in China's GEM such as deviating from intrinsic value, high initial returns and from the point to improve pricing efficiency and effectiveness, this paper combines Analytic Hierarchy Process(AHP) with BP Neural Network to establish a new IPO pricing model. Firstly, we applies AHP to construct a comprehensive pricing assessment index system and screens the assessment indexes according to their weights. Then, we carries out example simulations with BP Neural Network model. The results indicate that the combination model of Analytic Hierarchy Process with BP Neural Network model is effective in fixing the prices of new issues in China's GEM.