https://github.com/jaungiers/LSTM-Neural-Network-for-Time-Series-Prediction

LSTM built using Keras Python package to predict time series steps and sequences. Includes sin wave and stock market data
https://github.com/jaungiers/LSTM-Neural-Network-for-Time-Series-Prediction

Last synced: 2 months ago
JSON representation

LSTM built using Keras Python package to predict time series steps and sequences. Includes sin wave and stock market data

• Host: GitHub
• URL: https://github.com/jaungiers/LSTM-Neural-Network-for-Time-Series-Prediction
• Owner: jaungiers
• License: agpl-3.0
• Created: 2016-12-18T16:26:20.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2023-03-24T21:54:57.000Z (almost 2 years ago)
• Last Synced: 2024-10-29T15:29:35.071Z (2 months ago)
• Language: Python
• Size: 396 KB
• Stars: 4,821
• Watchers: 253
• Forks: 1,956
• Open Issues: 49
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome_time_series_in_python - LSTM-Neural-Network-for-Time-Series-Prediction
• awesome-time-series - LSTM-Neural-Network-for-Time-Series-Prediction

README

        
# LSTM Neural Network for Time Series Prediction

LSTM built using the Keras Python package to predict time series steps and sequences. Includes sine wave and stock market data.

[Full article write-up for this code](https://www.altumintelligence.com/articles/a/Time-Series-Prediction-Using-LSTM-Deep-Neural-Networks)

[Video on the workings and usage of LSTMs and run-through of this code](https://www.youtube.com/watch?v=2np77NOdnwk)

## Requirements

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

* Python 3.5.x

* TensorFlow 1.10.0

* Numpy 1.15.0

* Keras 2.2.2

* Matplotlib 2.2.2

Output for sine wave sequential prediction:

![Output for sin wave sequential prediction](https://www.altumintelligence.com/assets/time-series-prediction-using-lstm-deep-neural-networks/sinwave_full_seq.png)

Output for stock market multi-dimensional multi-sequential predictions:

![Output for stock market multiple sequential predictions](https://www.altumintelligence.com/assets/time-series-prediction-using-lstm-deep-neural-networks/sp500_multi_2d.png)