Microsoft machine learning hackathon results in May
Hello!
At the end of May 2016, we successfully completed the third hackathon for machine learning. The topic of advanced data analysis in recent years is gaining increasing popularity, and we are pleased to contribute to its development. For two days we gathered more than 150 people under the roof of our office, who, during a short acquaintance with each other, quickly chose the captains and divided into 24 teams.
The hackathon participants were offered a choice of solving 4 data modeling tasks and 1 visualization task using Microsoft technologies: the Azure Machine Learning machine learning service and the Power BI business intelligence service.
Customers whose business problems the participants had to solve for two days were:
More information about the tasks can be found on the event website .
')
At the end of the first day, we identified the best in the data visualization nomination, the winner of which was the “Small data” team, which received the Nokia Lumia 650 phone as a prize. The team made some beautiful and representative dashboards and also used an unusual clustering technique customers.
Congratulations to the team captain Sergey Chernov and the team itself with a victory!
Other teams also demonstrated interesting data interpretation options:
At the end of the second day, the modeling decisions were defended before the jury
The winners of the Mother and Child task were the ZeroBit team (RMSE = 1 325 097.9).
The best solution for the “Business Youth” task was demonstrated by the “5 seconds to win” team (AUC = 0.634199).
Since no team showed satisfactory business results for the Bank and the Magnitogorsk Metallurgical Plant, it was decided to extend Hackathon until May 29 and allow participants to continue competing for prizes remotely. According to the results, announced at the beginning of June, the best result in solving the MMK problem was left to the Catalysis team (captain - Alexander Orlov), and according to the results of solving the bank's problem, the Home CR team (captain - Shabalin Mikhail) took the lead. However, the prize was not given to the team that solved the CMI problem, since the result obtained did not meet the accuracy criterion set by the customer.
At the moment, we continue to communicate with the captains of these teams and customers in order to maximize the quality of the results.
Valuable assistance in conducting the event and evaluating the decisions were provided by invited experts who demonstrated a high level of knowledge of machine learning technologies.
The experts at the event were:
We thank everyone who has been with us these two days, we will be happy to receive feedback,
and we are waiting for everyone on the new hackathons!
At the end of May 2016, we successfully completed the third hackathon for machine learning. The topic of advanced data analysis in recent years is gaining increasing popularity, and we are pleased to contribute to its development. For two days we gathered more than 150 people under the roof of our office, who, during a short acquaintance with each other, quickly chose the captains and divided into 24 teams.
The hackathon participants were offered a choice of solving 4 data modeling tasks and 1 visualization task using Microsoft technologies: the Azure Machine Learning machine learning service and the Power BI business intelligence service.
Customers whose business problems the participants had to solve for two days were:
- Magnitogorsk Metallurgical Plant (to determine the silicon content in the furnace)
- Business Youth Community of Entrepreneurs (categorize clients hot and cold)
- Network of clinics "Mother and Child" (to predict the sale of groups of services)
- And one of the largest Russian banks, which participated anonymously. (estimate future customer turnovers on transactions)
More information about the tasks can be found on the event website .
')
At the end of the first day, we identified the best in the data visualization nomination, the winner of which was the “Small data” team, which received the Nokia Lumia 650 phone as a prize. The team made some beautiful and representative dashboards and also used an unusual clustering technique customers.
Congratulations to the team captain Sergey Chernov and the team itself with a victory!
Other teams also demonstrated interesting data interpretation options:
At the end of the second day, the modeling decisions were defended before the jury
The winners of the Mother and Child task were the ZeroBit team (RMSE = 1 325 097.9).
The best solution for the “Business Youth” task was demonstrated by the “5 seconds to win” team (AUC = 0.634199).
Since no team showed satisfactory business results for the Bank and the Magnitogorsk Metallurgical Plant, it was decided to extend Hackathon until May 29 and allow participants to continue competing for prizes remotely. According to the results, announced at the beginning of June, the best result in solving the MMK problem was left to the Catalysis team (captain - Alexander Orlov), and according to the results of solving the bank's problem, the Home CR team (captain - Shabalin Mikhail) took the lead. However, the prize was not given to the team that solved the CMI problem, since the result obtained did not meet the accuracy criterion set by the customer.
At the moment, we continue to communicate with the captains of these teams and customers in order to maximize the quality of the results.
Valuable assistance in conducting the event and evaluating the decisions were provided by invited experts who demonstrated a high level of knowledge of machine learning technologies.
The experts at the event were:
- Alexander Fonarev, Alexander Kuzmin and Mikhail Gavrikov from Rubbles, a member of the SBDA Group. Rubbles specializes in the application of machine learning and data analysis methods for various business tasks - for example, to personalize marketing and banking services, build intelligent chat chat platforms, or predict demand in
major stores. Now Rubbles is working with the largest financial
and technology companies (Sberbank, Mastercard, Alfa-Bank,
Qiwi, HSBC and others). - Oleg Kharatov from Manzana Group, an IT consulting company, is a Microsoft Gold Certified Partner.
- And also: Alexey Peshekhonov, Evgeny Grigorenko and Dmitry Petukhov ( @codezombie ) .
We thank everyone who has been with us these two days, we will be happy to receive feedback,
and we are waiting for everyone on the new hackathons!
Source: https://habr.com/ru/post/303206/
All Articles