https://github.com/nkid00/futurecrypto

Predict the future BTCUSDT cryptocurrency exchange prices using neural network.
https://github.com/nkid00/futurecrypto

cryptocurrency machine-learning nueral-networks prediction recurrent-neural-networks

Last synced: 3 months ago
JSON representation

Predict the future BTCUSDT cryptocurrency exchange prices using neural network.

• Host: GitHub
• URL: https://github.com/nkid00/futurecrypto
• Owner: NKID00
• License: mit
• Created: 2021-07-19T14:11:39.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2021-07-25T01:14:24.000Z (about 4 years ago)
• Last Synced: 2025-01-22T18:52:32.581Z (9 months ago)
• Topics: cryptocurrency, machine-learning, nueral-networks, prediction, recurrent-neural-networks
• Language: Python
• Homepage:
• Size: 24.4 KB
• Stars: 1
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
## FutureCrypto

Predict the future `BTCUSDT` cryptocurrency exchange prices using neural network.

## Usage

1. Install the dependences:

   ```sh

   $ pip install -U numpy tensorflow matplotlib

   ```

2. Build the `BTCUSDT` dataset using [CryptocurrencyPriceDataset](https://github.com/NKID00/CryptocurrencyPriceDataset).

3. Create a symbolic directory link named `data` targeting the `data` directory containing the datasets.

4. Modify `./config.py` if needed.

5. Run this script to preprocess the data:

   ```sh

   $ python ./preprocess.py

   ```

   Preprocessed data is saved in `./preprocessed/BTCUSDT.npz`.

6. Run this script to train the model:

   ```sh

   $ python ./train.py

   ```

   Trained model is saved on every epoch in `./model/__/`.

   Or run this script to restore semi-trained model from the latest epoch:

   ```sh

   $ python ./restore.py

   ```

7. Run this script to plot the prediction (and real values):

   ```sh

   $ python ./plot.py

   ```

## Model Structure

```

┌────────────┐

│ InputLayer │

└─────┬──────┘

      │

┌─────▼─────┐

│    GRU    │

└─────┬─────┘

      │

┌─────▼─────┐

│   LTSM    │

└─────┬─────┘

      │

┌─────▼─────┐

│   Dense   │

└─────┬─────┘

      │

┌─────▼─────┐

│   Dense   │

└───────────┘

```