Here, we present the model's performance in predicting the bitcoin price along with their hyper-parameters. For more details on the model, see here.
| DATE | CLOSE |
|---|---|
| 2024-12-18 | 97,721.70 |
| 2024-12-25 | 96,634.90 |
| 2025-01-01 | 98,192.11 |
| 2025-01-08 | 102,223.89 |
For scoring, Root Mean Squared Error was used.
| D+7 | D+14 | D+21 | D+28 |
|---|---|---|---|
| 729.92 | 429.23 | 504.52 | 1,423.07 |
| D+7 | D+14 | D+21 | D+28 |
|---|---|---|---|
| 7,163.80 | 2,373.11 | 1,120.98 | 7,881.91 |
Below are choices made for the model setup.
(Determined by Forward Selection and heuristically based on the model's assumptions)
| param | description | value |
|---|---|---|
| include_indices | Whether to include market indices. | True |
| include_commodities | Whether to include commodities. | False |
| include_currencies | Whether to include currencies. | False |
(Determined by Grid Search)
| param | description | value |
|---|---|---|
| ohlc_ratio | Whether to add OHLC ratios of bitcoin price to the data. | True |
| lags | List of lags to use. None, if no lags are used. | None |
(Determined by heuristically, considering the model's assumptions)
| param | description | value |
|---|---|---|
| log | Whether to take the log of the data. | True |
| diff | Whether to difference the data. | True |
| normalize | Whether to normalize the data. | True |
(Determined by Grid Search)
| param | description | value |
|---|---|---|
| hidden_dim | The hidden dimension of the LSTM. | 5 |
| num_layers | The number of layers of the LSTM. | 4 |
| seq_len | The sequence length to use for training. | 28 |