/SBER-LSTM-Neural-Network-for-Time-Series-Prediction

Primary LanguagePythonGNU Affero General Public License v3.0AGPL-3.0

LSTM Neural Network for Time Series Prediction - for SBER

LSTM built using the Keras Python package to predict time series steps and sequences. For SBER stock market data.

My realization for SBER price prediction.

We need to normalize data properly in order to get right prediction.

We can use multi dimensional data input for our model.

Please be aware! This model is only DRAFT - not real for stock price predictions.

Wait for the next video with the Full review of structure for model.

How to get stock data in real time: see this code

Jupyter Notebook with some of this code is here.

Requirements

Install requirements.txt file to make sure correct versions of libraries are being used.

  • Python 3
  • TensorFlow
  • Numpy
  • Keras
  • Matplotlib

Some code was taken from here.