International Data Science Game 2016
The Data Science Game is a French association run by volunteer data scientists and students, supported by Paris-Saclay University. The international competition brings together teams of students from the best data science, computer science, statistics and applied mathematics programmes around the world to solve a real-world problem. To stand out in this competition, students have to implement predictive models related to Big Data issues.
This year, 143 teams, representing more than 50 universities from 28 countries participated in an online competition from 17 June to 10 July. During this first phase, competitors had to find the best solutions to a predictive problem involving massive and complex data, using statistical algorithms to treat and figure out this data.
Contestants addressed the future issue of optimising solar energy production in the first phase. To map solar energy production potential in France, the OpenSolarMap project provided satellite images of roofs of 80,000 buildings. The contestants had to develop an algorithm able to recognise the orientation of a roof from a satellite photograph by building on more than 10,000 photographs of roofs which were categorised through crowdsourcing.
After 24 days of competition and 831 algorithms submitted by the 143 teams, the NUS Science team - Data Ninja - came in ninth in the first phase. They emerged the top team in Asia, with a ranking higher than other prestigious universities from the United States, Japan and India.
The Data Ninja team comprises WANG Weimin, a part-time Statistics Master’s student specialising in machine learning, data science and statistics and three teammates from NUS’ Institute of Systems Science (ISS). In his work as a Data Scientist in MSD Singapore, Weimin focuses on bioinformatics research and advanced analytics projects.
The 20 best teams were invited to Paris on 10 to 11 September to compete in the final stage of this international hackathon. In the finals, the students were welcomed to the Château Les Fontaines, the training and development campus of the Capgemini Group. During the competition, contestants had the opportunity to tap on the expertise and knowledge of data scientists from Axa and its Data Innovation Lab, Capgemini, Microsoft and independent actuarial firm Milliman, to solve a data analysis challenge.
Weimin said, “Everyone in our team made great contributions during the first round. It was a valuable opportunity to work with my teammates, who are all top experts from this industry! Even a best player will find it hard to beat a strong team. I learnt the importance of teamwork from this competition.”
The NUS Science team competed against some of the world’s top universities in the finals, including University of Cambridge, Stanford University, Northwestern University, Columbia University, to name a few. They have emerged sixth in the Final Leaderboard and third in the Public Leaderboard.
Kudos to Weimin and the team!
Results may be viewed at this link.
Weimin (second from right) with the other members of the Data Ninja team
In discussion during the competition
Well done, Team Data Ninja!