The Application of NAR Dynamical Neural Network on Quantitative Investment

By choosing 2536 trading days' (from Jan. 4, 2007 to June, 9, 2017) Shanghai (Opening Price) and Shenzhen securities composite index (Opening Price) as the sample data used for empirical analysis, We established the NAR dynamic neural network and training neural network. The trained network is used to predict security index and the predicting effect will evaluated, we further proven the feasibility of applying NAR dynamic neural network for quantitative investment.