## Important Dates:
- Kaggle Competition Release Date: 14th March 2025
- Kaggle Competition Deadline: 4th April 2025
- GenAI Integration Paper Deadline: 18th April 2025

## Submission Format on Canvas
**1. GenAI Integration Paper**: 
- Name your paper with your NUS Student Number, i.e. **A0123456Z.pdf**. 
- Length: 2-3 pages (excluding references)
- Format: PDF
- Use the following templates from ACL: https://2023.aclweb.org/calls/style_and_formatting/
- Include tables and graphs in an appendix (2 pages limit)
- Citations for AI tools and resources used

**2. Jupyter Notebook**: 
- Submit a Jupyter notebook (.ipynb) for the final model for your top submission, together with your paper. Name this file with your NUS Student Number, i.e. **A0123456Z.ipynb**.
- Note: Your notebook should be in working condition. That means after reading your report the grader might try to run all cells of the notebook. If the notebook fails to run it might attract some penalty. Thus don’t leave dangling code in the notebook and test the notebook yourself once before submitting.

##Required GenAI Integration Paper Submission
**1. AI Tool Selection and Strategy**
- Description of chosen AI tools (e.g., ChatGPT, Claude, GitHub Copilot, Cursor, Devin)
- Rationale for tool selection
- Integration strategy with traditional ML pipeline

**2. Implementation and Usage**
- Detailed examples of AI tool usage in the competition (not limited to the following):
    - Data preprocessing and feature engineering
    - Model selection and architecture design
    - Code optimization and debugging
    - Result analysis and interpretation
- Document prompt engineering strategies
- Show iterations and refinements in AI interactions
- Demonstrate understanding of AI tool capabilities and limitations
- Here, participants are encouraged to document specific cases where AI tools failed or hindered development, including incorrect suggestions, increased complexity, or debugging difficulties and provide in-depth analysis.
    - Analysis should include root causes of AI failures and practical recommendations for when to avoid AI tool usage in similar scenarios.

**3. Impact Analysis**
- Quantitative/Qualitative assessment of AI tool impact on:
    - Development time and efficiency
    - Model performance
    - Code quality
- Critical evaluation of AI tool limitations
- Lessons learned and best practices identified