An Improved BPNN Algorithm Based on Deep Learning Technology to Analyze the Market Risks of A+H Shares

The backpropagation neural network (BPNN) algorithm of artificial intelligence (AI) is utilized to predict A+H shares price for helping investors reduce the risk stock investment. First, genetic (GA) used optimize BPNN, and a model that can multi-day prices established. Then, Principal Component Analysis (PCA) introduced improve GA-BP model, aiming provide practical approach analyzing market risks shares. experimental results show A shares, has best prediction effect on Bank China (BC), average errors opening price, maximum minimum as well closing are 0.0236, 0.0262, 0.0294 0.0339, respectively. For H constructed Merchants (CMB). 0.0276, 0.0422, 0.0194 0.0619,