Stock Index Futures Trading Based On Deep Learning

Since the early1980s,the artificial neural network technology has been develop-ing rapidly around the whole world,it was the mathematical model that is established on the basis of the simulation of the human brain structure and thinking.It also can solve many problems such as image recognition,speech recognition,natural language process-ing, which have caused the high attention of scholars in the domestic and abroad.2006Hinton and others proposed the concept of deep learning on the base of artificial neural network.Deep learning is the neural network of the depth that contains a lot of hidden layer.It has more excellent ability about characteristics of learning and can abstract and expression data more essential.Deep learning optimize the training process of the data model by initializing data one by one,and then improve the accuracy of the model pre-diction classification. In the past two years,the use of deep learning methods to deal with the high-frequency financial data sets off a wave of the rise of research and ap-plication.However the point is how to choose the appropriate initialization model ac-cording to the data features. It established a model of stock index futures and made a comparative analysis by using the auto-encoder machine and Restricted Boltzmann ma-chine theory that combined the artificial neural network in the paper. Finally it build a trading system according to the trading strategy in the paper.The model can be roughly divided into four parts:data preprocessing module,neural network initialization mod-ule,deep learning module,the trading strategy module.