Hamburg News: Trade and Finance. High-class shopping area in the city centre shown.
OttoGroupHamburg © Otto Group

Business Intelligence: Otto Group Started Data Science Challenge

To solve complex IT issues, Otto Group is increasingly involving international communities. Competitions launched on Kaggle to close 18 May 2015

The Hamburg retailer and services provider Otto Group is the first German company to have launched a challenge on Kaggle, the world’s largest Internet platform for Data Science competitions.

Otto Group Starts Global Product Classification Challenge

In the competition, participants are challenged to create a model to correctly classify products between nine product categories (fashion, electronics, etc.). The data consists of 200,000 products with 93 features each. The features have been obfuscated so it’s hard to make any subjective inferences about them. Launched on 19 March 2015, the contest will be running until 18 May 2015.

Main Target: To Unify Categories

“We are a global group of companies with more than 100 online shops, each offering different products on a different IT infrastructure. To make possible a comprehensive analysis of the global sales of individual products, it must be possible to assign the products to single categories. A manual assignment of all products is not only time consuming, but also error-prone”, comments Josef Feigl, Data Scientist at Otto Group, on the task.

Challenge Endowed With 10,000 US Dollar

Founded in 2010, Kaggle features competitions launched by companies on data-based business questions. Experts from around the world are invited to find an answer and to compete in a contest for the best algorithm. The Kaggle competition of the Otto Group will be running for two months. The best three solutions will be rewarded with a total prize money of 10,000 US dollars. In the first two days since the launch, more than 400 participants have already participated in the contest that also received positive feedback in numerous forums.

source and further details:

More articles

  • There are no older articles in this category.
  • There are no newer articles in this category.