Predicting trading strategies using LSTM.
This project shows how LSTM based deep neural networks can be applied to predict time series financial data. “The average reduction in error rates obtained by LSTM is between 84 - 87 percent when compared to ARIMA indicating the superiority of LSTM to ARIMA. Furthermore, it was noticed that the number of training times, known as "epoch" in deep learning, has no effect on the performance of the trained forecast model and it exhibits a truly random behavior.”
* NumPy (1.16.2)
* Matplotlib (3.0.2)
* TensorFlow (1.13.1)
* Pandas (0.23.4)
* h5py (2.8.0)