Submissions are evaluated based on Mean Squared Error (MSE) between the predicted Close values and the actual observed values in the test set. MSE is calculated as the average of the squares of the differences between the predicted and actual values, providing a clear metric for assessing the accuracy of predictions.

## Submission File

For each ID in the test set, you must predict the Close value for the target variable. The submission file should contain a header and follow this format:

| ID | CLOSE |
| -- | ------- |
| 4995 | 150.25 |
| 4996| 152.00 |
| 4997 | 149.75 | 
| ... | ... |
| 6243 | 223.5 |

Make sure that the IDs correspond to those in the test set and that your predicted Close values are in the appropriate format. 
Similar to the sample submission, the IDs should range from 4995-6243 in your submission.

## E.g. code using Scikit learn

```python
# assume model is already loaded and tuned
# create your predictions
y_pred = model.fit(y_test)

# assume you have loaded the sample_submission.csv, copy df and change Close column
my_solution = sample_solution.copy(deep=True)
my_solution['Close'] = y_pred

# save as csv
my_solution.to_csv('my_solution.csv')
```