Model description
This model predicts Apple stock prices. The model takes as input the last 500 daily candles of Apple stocks data and outputs the predicted candle for the next day. The input candles must be in chronological order, representing daily data for each candle, and the predicted candle will also be in daily format.
Intended uses & limitations
This models is intended to be used as a learning project. Please don't use it as a financial tool. The only place where it should be running is the following space:
Training and evaluation data
The training and evaluation data is the obtained using the pandas_datareader from the yahoo finance data between 2013-01-01 and 2023-04-05. The data was split into a 80:20 ratio for training and evaluation, respectively.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
| Hyperparameters | Value |
|---|---|
| name | Adam |
| weight_decay | None |
| clipnorm | None |
| global_clipnorm | None |
| clipvalue | None |
| use_ema | False |
| ema_momentum | 0.99 |
| ema_overwrite_frequency | None |
| jit_compile | False |
| is_legacy_optimizer | False |
| learning_rate | 0.0010000000474974513 |
| beta_1 | 0.9 |
| beta_2 | 0.999 |
| epsilon | 1e-07 |
| amsgrad | False |
| training_precision | float32 |
Model Plot
View Model Plot
- Downloads last month
- 0