2018 – For the fourth year in a row, Data Science Game has its champion!
Since its creation, the Data Science Game gathered more than 2500 students from all around the world to compete on deep learning, text-mining and predictive modelling algorithms to defend the colours of their university. For its fourth edition, more than 30 countries were represented. During one month, students in data science faced a real-world, demanding and innovative business challenge for the qualification phase. The final phase, held in Paris, saw the 80 best students fiercely competing for the title of Data science Champion.
Awarding the students who succeeded in placing their Data Science skills at the service of innovative business issues.
To qualify for the finals, the teams helped BNP Paribas improving its customer service using Machine Learning algorithms to predict customer interest in specific bonds available in the market.
Again this year, the competitors handled the complexity of a real-life business issue by taking into account the differences between the customers. Indeed, investors may be interested in a specific category of bonds, or may have different strategies.
Overall, the students had to mobilize their machine learning skills and be creative in order to capture rare events. This qualifying challenge gave the students the opportunity to prove their worth and their ability to build innovative methods to offer to businesses the best of Machine Learning and Data Science.
The 20 best data science universities worldwide supported by key contributors to the field of Data Science, competed to conceive and implement the most innovative and efficient predictive algorithm.
During the finals, the “crème de la crème” of data science education gave the best of their data science knowledge and programing experience to get the highest predictive scores and to help e-commerce industry transforming its business. The finalists faced difficult challenges, mixing sequential data and unstructured information. Students had to handle navigation tracking data to predict the probability that a purchase action occurs before the end of the navigation.
This year once again, Data Science Game was a resounding success thanks to its partners’ support, who are all key contributors in the field of Data Science. For the final phase, the students were welcome in the “Château Les Fontaines”, the training and development campus of the Capgemini Group. Microsoft provided its support by giving free and full access to its Azure services while the final challenge was set by Cdiscount. A 30 hours hackathon witnessed the creation of some of the most innovative and refined solutions to the problem, : the best team achieved a score (log-loss) of 0.2540. To assess teams, Data Science Game used this year a very robust and well designed open source challenge platform called Qscore (developed by Zelros and deployed on Microsoft Azure for the finals).
In this challenge, the best teams distinguished themselves thanks to smart and efficient feature engineering taking into account the complex sequential economic paths and constraints, and a deep knowledge of machine learning and statistics to compound the different models into powerful approaches. To stand out in this challenge, our 80 ambassadors had to find the most innovative algorithm while managing their time and team work.
2017 – The best Data Science students in the world compete in the Data Science Game
For the third year in a row, the Data Science Game will see Data Science students from around the world compete in this prestigious competition. This year, about 340 teams, representing more than 250 universities from 40 different countries will face a real-life demanding and innovative business challenge. To stand out in this competition, students will have to imagine and implement predictive models related to Big Data issues.
Striving for world-class excellence in Data Science; Moscow State University scoops top position at the Data Science Game 2017
2016 – A world-class competition
For the second year in a row the Data Science Game, a data science and machine learning international student contest, was held in Paris, France in September, 2016. 143 teams, three times as much as in 2015, representing more than 50 universities from 28 different countries (view the map), faced real-life business challenges. To stand out in this competition, students were asked to conceive and implement predictive models in order to solve Big Data-related issues.
A thrilling qualifier on computer vision and renewable energy
The 143 teams were first cut down to 20 through an online qualification phase which lasted for about a month. During this stage, candidates were given a challenge based on solar energy production optimization.
In order to map such production potential in France, the Data Science Game partnered with Etalab – the French public agency in charge of Open Data and Data use in the French administration. The State Agency created the OpenSolarMap project which provides satellite images of about 80,000 building roofs. Automated classification of roof orientation is a true challenge for Etalab.
For the 2016 Data Science Game participants, the challenge was to develop an algorithm which would recognise the orientation of a roof based on a satellite photograph by building on more than 10,000 roof photographs categorized using crowdsourcing. The majority of the top 40 teams used Deep Learning methods, which have proved to be particularly efficient on Computer Vision issues and in the context of Big Data.
A unique setting for the Data Science world finals
The final phase was held in the Château Les Fontaines in Paris area, France. The gathering saw 80 students competing in a fierce hackathon to build the best predictive algorithm, using Machine Learning models. This time, the challenge dataset contained requests for automobile insurance quotes received by AXA, the 1st international insurance brand, from different brokers and comparison websites.
The participants were asked to predict whether the person who requested a given quote bought the associated insurance policy. The mammoth 30-hour hackathon fostered the creation of some of the most innovative and refined solutions to this insurance-related problem.
The Moscow Institute of Physics and Technology (Russia), Cambridge University (United Kingdom) and Skoltech University (Russia) won the three first prizes, while Université Pierre et Marie Curie (France) and University of Padova (Italy) ranked 4th and 5th, respectively.
|Prize Capgemini, for 1st place||Russian Data Mafia||Moscow Institute of Physics and Technology||Russia|
|Prize AXA, for 2nd place||Cantab||Cambridge University||United Kingdom|
|Prize Microsoft, for 3rd place||We just want our name to be the longest one||Skoltech University||Russia|
|Prize Milliman, for 4th place||Jonquille||Université Pierre et Marie Curie||France|
|Prize Numberly, for 5th place||Brosio2BeWild||University of Padova||Italy|
|Prize QuantCube Technology, for Jury’s innovation prize||ml_noobs||Moscow State University||Russia|
Shortlisted countries included: France, the Netherlands, Russia, Germany, the UK, Singapore, USA, Japan, India, and Italy.
Last year’s edition saw an amazingly high level of competition. We are looking forward to seeing even more highly-skilled students in Data Science competing this year. Stay tuned for more information on the 2017 qualifier phase!