Machine Learning Hackathon

This hackathon is designed to challenge participants on their machine learning knowledge and practical skills through two rounds - one online and one offline.

Eligibility:

• Open to all college students.
• Participants can form teams of up to 4 members.

Round 1: Online Quiz:

• All registered participants must attempt an online, time-bound quiz covering core machine learning concepts.
• The quiz must be completed in one sitting without external assistance or bots.
• The top 30 teams, based on cumulative scores, will qualify for the next round.

Round 2: Offline Hackathon:

• Qualified teams (up to 30) will participate in an offline hackathon event.
• A common Problem statement will be shared in the presence of all teams.
• Teams will have a fixed duration to develop a machine learning project from scratch.
• All work must be completed during the hackathon period; pre-existing code is not allowed except for open-source libraries and frameworks.
• Teams must submit:
• Project code (with clear documentation)
• Dataset(s) used
• Detailed project report (problem statement, solution approach, model architecture, evaluation metrics, and real-world application)
• Project presentation (for final evaluation)

Team Formation:

• Teams can have a maximum of 4 members.
• Teams must be finalized before the start of Round 2.
• Each team must designate a representative for communication with organizers.

Project Guidelines:

• All projects must be original and developed during the hackathon.
• Use of open-source libraries, frameworks, and public datasets is permitted.
• Clearly document any external resources or code used.
• Projects must adhere to ethical AI practices and responsible data usage.
• Any continuation of previous work must be disclosed, and only new features or improvements will be judged.

Judging Criteria:

Projects will be evaluated based on the following:

• Technical Accuracy (50%) – Correctness and robustness of ML methods and implementation.
• Innovation & Creativity (20%) – Originality of the idea and solution approach.
• Execution & Functionality (15%) – Working prototype, code quality, and usability.
• Presentation & Clarity (15%) – Effectiveness of project explanation and visual aids.
• Judges will use a rating scale (e.g., 1–10) for each criterion to ensure fairness and consistency.
• In case of a tie, the team with stronger technical accuracy will be ranked higher.

Submission Requirements:

• Submit all code in a well-documented GitHub repository.
• Include a detailed report (PDF/Markdown) covering:
• Problem statement
• Dataset(s) used
• Model architecture
• Evaluation metrics
• Results and analysis
• Prepare a project presentation (slides) for the final demo session.
• All submissions must be completed before the announced deadline; late submissions will not be accepted.

Prohibited Activities:

• No use of bots, AI assistants, or external help during the quiz or hackathon.
• No plagiarism; all work must be original.
• No re-use of code written before the hackathon except for open-source libraries/frameworks.
• Any violation of rules, code of conduct, or unsporting behavior will result in immediate disqualification at the organizers’ discretion.

Code of Conduct:

• All participants must maintain a respectful and inclusive environment.
• Harassment, discrimination, or inappropriate behavior will not be tolerated and may result in disqualification.

General Terms:

• Organizers reserve the right to modify the rules, disqualify participants, or cancel the event in case of unforeseen circumstances.
• All decisions by the judging panel and organizers are final and binding.