IIT Madras Alumni Association announces top 50 teams in Machine Learning Hackathon Contest

IIT Madras Alumni Association announces top 50 teams in Machine Learning Hackathon Contest

New Delhi, August 12: The top 50 teams in its Machine Learning Hackathon Contest have been declared by IIT Madras Alumni Association (IITMAA). Delivering a strategy document for ‘Reimagining India in 2030’ to the Prime Minister’s Office (PMO), the Hackathon is a part of its Annual Flagship Event ‘Sangam’. These steps are planned to be part of the alumni’s contribution to the growth of the country. This year, IIT Madras is celebrating its Diamond Jubilee (60 years).

Collection of traffic volume patterns, climate conditions

An Indian Smart City’s Traffic Police Department willing to use Machine Learning/Artificial Intelligence techniques for solving their traffic crisis is involved in the scenario for the Hackathon. Observed for over four years, traffic volume patterns and climate conditions have been also collected by the department. Aiding the police in the prediction of traffic volume for given duration and climate conditions was the given task for the students participating in the Hackathon.

In Phase 1 online Hackathon, a total of 3,266 teams took participation with the top teams making predictions with an accuracy of up to 99.97 per cent. They used regression models such as ‘XGBoost’, supported by adept feature engineering techniques.

Along with Indian Statistical Institute, National Institute of Technology – Jamshedpur, National Institute of Technology – Patna and Army Institute of Technology – Pune, the top 50 teams of the first phase were from institutions across India including IIT Bombay, IIT Delhi, IIT Kharagpur, IIT Roorkee and IIT Madras as well.

Demographics of participants

  • Delhi NCR- 257 teams
  • Mumbai and Pune- 288 teams
  • Chennai and Hyderabad- 509 teams
  • Bengaluru- 437 teams
  • Kolkata- 103 teams
  • Coimbatore- 50 teams
  • Other parts of the country- 1,622 teams

On August 24 and 25, IITMAA will conduct Phase 2 of Hackathon onsite at the IIT Madras campus.

“Such highly accurate AI / ML models and analysis can not only help Indian Traffic Governance Systems predict and thereby, effectively manage, the traffic volume for a defined time period but also help analyze a trend to observe the correlation between Air Pollution Index and Traffic Volume,” Mr. Krishnan Narayanan, Co-Chair, Sangam 2019 and President, itihaasa Research and Digital, said while speaking on the importance of Hackathon and how the community will be helped by it at large.