# BT5153-2025-Whales Prediction Challenge — Data

来源：https://www.kaggle.com/competitions/BT5153-2025-whales-prediction-challenge/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Competitors are provided with two rich datasets:

**User Profile Data**: This dataset encapsulates a variety of user-specific attributes to help model financial behavior, including:
   - `user_id`: A unique identifier for each user.
   - `mobile_brand_name`, `mobile_marketing_name`: Information on the user's mobile device.
   - `age_in_year`, `gender_name`, `marital_status`, `education_background`, `income_level`, `occupation`: Demographic and socio-economic details of the user.

**Transaction Data** (April 1, 2022, to May 31, 2022): This dataset details users' financial activities, providing a lens into their transaction habits through attributes such as:
   - `asset_type`, `transaction_time`, `transaction_type`, `GTV`: Specifics of each transaction.
   - `user_id`: Links back to the user profile for integrated analysis.

The challenge is to use this data to forecast the transaction volume category ("high" or "low") of users in June 2022, thereby identifying potential "whales."

Training data is provided in `train_label.csv`. It has two attributes: `user_id` and  `tgt` that indicates users'tag: 1 indicates Whales while 0 is Normal Users

**Output Data**:
- Submissions must be in a CSV format with two columns: `user_id` and `pred_prob`, where:
  - `user_id` is the unique identifier for each user.
  - `pred_prob` is the model's prediction of the likelihood (between 0 and 1) that the user is a "whale."
- Participants can submit up to 3 entries per day.
- **Example Submission Format**: you can check `submission_sample.csv`