Improved optimization model for forecasting stock directions (FSD)

The study of stock market price predictions is very important. Recurrent Neural Network (RNN) has shown excellent results with this issue. There are two significant problems using strategy. One that it constantly struggles extensive neural network construction efforts and hyper-parameter adjustments. Two, often fails to come up a superior answer. suggested model proposed optimize the topology hyper-parameters RNN model. utilized for effective forecasting directions in research. Additionally, Improved Differential Evolution (IDE) method used tune RNN's hyperparameters their best potential. Utilizing IDE helps achieving direction prediction possible. Stock Prediction (SP) changes been accurately predicted by being presented. A series tests on popular benchmark datasets (AAPL FB) revealed superiority over other strategies accuracy 99.02% loss close 0.1% training testing.