Prediction of Stock Based on Convolution Neural Network

With the increasingly close connection between the market and computer technology. Stock forecasting is one of the task studies on the market economy. However, the information about the market economy contains a lot of noise and uncertainty, which makes the economic forecast more and more challenging. Ensemble learning and deep learning are the main methods to solve the stock forecast problem. In this paper, we forward a model combination of two methods, the advantages of two methods to forecast the change of stock price. The proposed method combines CNN and GBoost. The results of two market indexes show that this method has better performance for current popular methods.