Currently, the world economics develops rapidly, and the finance business also develops promptly. As there are more financial activities, the uncertainty of change trend in financial activities is also increased constantly. How to study and grasp the laws of banking activity and calculate their coming tendency has grown into the concentrate and major study substance of scientific and monetary ring. On the one hand, available finance prediction can supply base for making finance plans and relevant decisions, thus ensuring the laudable expansion of the finance market and maximizing the benefits of profit organizations. However, on the other hand, convolution neural network (CNN) is a multilayer neural network composition that can simulate the operation machine-made of biological field system, which can be used to obtain effective feature description. Meanwhile, the features are extracted from the original data. Now, CNN has turned into a study hot point in the fields of giving a lecture discriminate, figure distinguishing, and classifying, and natural language handling. Moreover, it is widely used in these fields, and its application effect has been recognized by most people. Consequently, CNN composition is adopted to predict the finance time succession data. Firstly, the research means of financial time series are summarized, and then, the artificial neural network (ANN) and deep learning methods are briefly introduced. Afterward, the prediction model of stock index according to CNN model is proposed, and the influences of historical factors on model are analyzed. Finally, a few stock indexes are predicted to verify validity and effectiveness of the proposed CNN model through experimental comparison. And a hybrid model combined with CNN is found, thus further improving the cable CNN network model.
