Stock Price Forecasting Based on Feature Fusion Deepar Model

Stock forecasting has always attracted the attention of the people. However, existing studies rarely use long-term price patterns as input features. Therefore, this paper proposes a new deep learning model that integrates the features of long-term price models to predict stock closing prices. The clustering algorithm is used to extract the features of the long-term price model, and the prediction model is selected based on the deep autoregressive model. The method of output probability distribution of this model is suitable for time series data with large uncertainty such as financial data. The way of maximizing the likelihood function of the future sequence can better reflect the inherent randomness of the data. It can not only predict the value, but also predict the future fluctuation, and has high prediction accuracy. Compared with other deep learning models, the results show that the feature fusion the deep autoregressive model has lower prediction error and higher goodness of fit.