Renewable energy company stock dynamics forecast in the period of sustainable development based on Fractal-FOA-LSTM

In stock trend forecasting system, feature selection and model building are two major factors that affect prediction performance. order to improve the accuracy of stability model, a Fractal-FOA-LSTM is proposed. Firstly, features selected by using FOA (fruit fly algorithm) combined with fractal dimension reduce redundancy features, indexes used as system input. And proposing double input LSTM(long-short term memory) network optimizing its parameters, it can select best parameters for different data automatically. This paper test on 4 sets UCI database Shanghai Composite Index proved method effective, through empirical analysis S&P500, compared results SVM PNN, verified feasibility superiority base fractal-FOA-LSTM.