The two-layer SRU Neural Network Based Analysis of Time Series

The traditional measurement model cannot meet the processing requirements of non-linear and high-noise time series data. A two-layer simple recurrent unit (DSRU) prediction based on BPSO SO-PMI sentiment analysis algorithm is proposed. First, uses to calculate stock market tendency index. Then used extract characteristics technical indicators with greater price correlation. Finally, DSRU network predict price. Taking Shanghai Pudong Development Bank as an example, results show that has a significant improvement in accuracy, reaching 65.84%, average absolute error 0.0541, which proves superiority effectiveness method.