This hackathons is only open to students. Double check the event page for more information as this may mean only those from a particular university/country are eligible.
Event Type
online
1,085
Participants
97
Est. Projects
Organizers
Alex Johnson
alex@example.org
Jamie Rivera
jamie@example.org
Sam Chen
sam@example.org
Quality Score
Quality Score
72/100
High confidence
Organiser16/20
Event Maturity14/20
Sponsors18/25
Participants12/20
Competition Overview:
Participants must build a robust machine-learning solution using a dataset involving nuts, washers, and related components.
The hackathon consists of two rounds:
Round 1: Kaggle ML Challenge + PPT Submission
Round 2: Prototype Presentation before Judges
Eligibility:
Open to all students from any college/university.
Participation allowed solo or in teams of up to 3 members.
Round 1: Kaggle Round + PPT Submission
Kaggle Round:
A private Kaggle competition link will be shared after registration.
Participants must build, train, and submit predictions on the test dataset.
Leaderboard ranking (public LB) determines performance.
External datasets or pre-trained models on similar domains are not allowed.
Code must be fully original — plagiarism or code-sharing leads to disqualification.
PPT Submission:
Teams must submit a PPT on Unstop covering:
Problem understanding
Approach and model architecture
Data preprocessing techniques
Feature engineering (if any)
Evaluation strategy
Dataset insights
Why the solution is scalable & reliable
Note: Round 1 selection is based on both the PPT + Kaggle score.
Round 2: Prototype Presentation (On-Campus)
Shortlisted teams will present their prototype at IIT Madras.
Teams must showcase:
Working prototype or model pipeline
Key insights from Round 1
Improvements made after the Kaggle round
Deployment feasibility or business relevance
General Rules:
Register before the deadline — no late entries accepted.
All decisions by the organizing committee/judges are final.
Teams must strictly follow deadlines and file formats.
Any unethical practice (plagiarism, model leakage, submitting others' work) leads to immediate disqualification.
Use of GenAI tools for coding/explanations: allowed/not allowed (customize as needed).
All communication and updates will be sent via email/Unstop dashboard.