Submissions are evaluated using **Area Under the Receiver Operating Characteristic Curve (ROC-AUC)** between the predicted probability and the observed binary target.

ROC-AUC measures the model’s ability to rank positive instances higher than negative ones across all possible classification thresholds. A perfect model achieves a score of 1.0, while a model with no predictive power scores approximately 0.5.

Higher scores indicate better ranking performance.

---

## Leaderboard Split

The leaderboard is divided as follows:

- **Public Leaderboard:** 30% of the test data  
- **Private Leaderboard:** 70% of the test data  

During the competition, participants see scores based only on the public portion. Final rankings are determined by the private leaderboard after the competition closes.

This split is designed to reduce leaderboard overfitting and encourage robust modeling.

---

## Submission Requirements

For each `customer_id` in the test set, you must predict the probability that the customer will make a purchase in the next 30 days.

Predictions must:

- Be numeric probabilities
- Be between 0 and 1
- Contain no missing values
- Match the order and IDs in `test.csv`

---

## Submission File Format

Your submission file must contain a header and follow exactly this structure:
customer_id,target 100001,0.8234 100002,0.1452 100003,0.5127 ...
Where:

- `customer_id` corresponds to the IDs in `test.csv`
- `target` is a predicted probability between 0 and 1

Files that do not follow this exact format will result in an error.

---

## Important Notes

- Submissions are limited to 5 per day.
- Up to 3 final submissions will be eligible for private leaderboard scoring.
- Accuracy is **not** the evaluation metric.
- Binary predictions (0 or 1) are allowed but strongly discouraged, as ROC-AUC rewards well-calibrated probability ranking.

---

We recommend validating your model using cross-validation strategies that reflect potential distribution shifts and avoid data leakage.