posted by organizer: skallumadi || 1008 views || tracked by 1 users: [display]

Ecom-Challenge 2018 : Rakuten Data Challenge: Taxonomy Classification for eCommerce-scale Product Catalogs

FacebookTwitterLinkedInGoogle

Link: https://sigir-ecom.github.io/data-task.html
 
When Jul 12, 2018 - Jul 12, 2018
Where Ann Arbor, Michigan, USA
Abstract Registration Due May 15, 2018
Submission Deadline Jun 1, 2018
Notification Due Jun 15, 2018
Categories    taxonomy classification   ecommerce   data challenge
 

Call For Papers

Call For Participation

The SIGIR eCom workshop is organizing a Data Challenge as part of the workshop. The data is provided by Rakuten Institute of Technology, Boston (RIT-Boston), a dedicated R&D organization for the Rakuten group.

The dataset has 1 million titles and ~3000 labels, unbalanced class sizes.

Challenge website: https://sigir-ecom.github.io/data-task.html

Important Dates:
Data Challenge Registration Deadline - May 15, 2018
System Description Paper Submission - June 1, 2018
Paper Acceptance Notification - June 15, 2018
Final Leaderboard - June 24, 2018
SIGIR eCom Full day Workshop - July 12, 2018

Task Description:

This challenge focuses on the topic of large-scale taxonomy classification where the goal is to predict each product’s category as defined in the taxonomy tree given product's title. The cataloging of product listings through taxonomy categorization is a fundamental problem for any e-commerce marketplace, with applications ranging from personalized search recommendations to query understanding.

For example, in the Rakuten.com catalog, “Dr. Martens Air Wair 1460 Mens Leather Ankle Boots” is categorized under the “Clothing, Shoes & Accessories -) Shoes -) Men -) Boots” leaf. However, manual and rule based approaches to categorization are not scalable since commercial product taxonomies are organized in tree structures with three to ten levels of depth and thousands of leaf nodes.

Advances in this area of research have been limited due to the lack of real data from actual commercial catalogs. The challenge presents several interesting research aspects due to the intrinsic noisy nature of the product labels, the size of modern eCommerce catalogs, and the typical unbalanced data distribution.

Participation and Data
The data challenge is open to everyone.

As part of this challenge, Rakuten will be releasing 1M product listings in tsv format, including the train (0.8M) and test set (0.2M), consisting of product titles and their corresponding category ID paths. Details about evaluation metrics and other aspects of the task can be found at the website: https://sigir-ecom.github.io/data-task.html

Related Resources

ICDMML 2020   【EI SCOPUS】2020 International Conference on Data Mining and Machine Learning
ISBDAI 2020   【Ei Compendex Scopus】2020 International Symposium on Big Data and Artificial Intelligence
Journal Special Issue 2019   Machine Learning on Scientific Data and Information
Data Science 2020   3nd Annual International Great Lakes Data Science Symposium
IEEE COINS 2020   Internet of Things IoT | Artificial Intelligence | Machine Learning | Big Data | Blockchain | Edge & Cloud Computing | Security | Embedded Systems | Circuit and Systems | WSN | 5G
IDA 2020   The 18th International Symposium on Intelligent Data Analysis (IDA 2020)
LSC 2019   Lifelog Search Challenge
DSIS 2020   2nd ISSAT International Conference on Data Science and Intelligent Systems
CISDM 2020   2020 2nd European Conference on Information System and Data Mining (CISDM 2020)
DSBFI 2020   2nd ISSAT International Conference on Data Science in Business, Finance and Industry