### 1. Competition Entry

* By participating, you agree to follow these rules.
* Only **one account per participant** is allowed. Submissions from multiple accounts are not permitted.

### 2. Team Limits

* Teams can have up to **4 members**.

### 3. Submission Limits

* Each participant or team can submit a maximum of **5 predictions per day**.
* Up to **1 submission** can be selected as the final submission for judging.
* **Random predictions will NOT be counted as valid submissions.**

### 4. Data Use

* The provided dataset can only be used for this competition.
* External data and tools are allowed if they are **publicly available and equally accessible** to all participants.

### 5. Evaluation

* Solutions will be assessed in two main areas:

  1. **Model Quality (80%)**

     * Historical daily price data
     * A hidden out-of-time (OOT) dataset will be used to assess model generalization
     * Participants train models on the provided historical data and submit predictions for the OOT period
     * Higher **Gini** indicates better ranking of positive vs negative cases
  2. **Code & Presentation Quality (20%)**

     * Clarity of the modeling approach and reasoning behind model selection
     * Explanation of feature engineering and preprocessing

### 6. Technical Requirements

* **Programming language:** Python
* **Allowed frameworks:** Any (e.g., PyTorch, TensorFlow, Scikit-learn, CatBoost, LightGBM, XGBoost, etc.)
* **External models:** Integration of LLMs or specialized APIs is permitted

### 7. Deliverables

* Training notebook/code
* Submission file (predicted probabilities for price increase)
* Short methodological report (slide deck or interface)

**Important:** Submissions consisting of random predictions will **NOT** be considered valid entries.