天池大赛

KDD Cup 2020 Challenges for Modern E-Commerce Platform: Debiasing_算法大赛_天池大赛


enter image description here

KDD Cup 2020 Challenges for Modern E-Commerce Platform:
Debiasing

1. Introduction

In 2019, retail e-commerce sales worldwide amounted to 3.53 trillion US dollars and e-retail revenues are projected to grow to 6.54 trillion US dollars in 2022. Such rapid growth promises a great future for the worldwide e-commerce industry signifying a strong market and increased customer demand. Besides the huge increment of the traffic volume, there has been a rapid growth of various upcoming modalities, including sales live streaming, experts or celebrities' shopping guides through blogs and lifestyle stories via short videos and photos, among many others. It is worth exploring the various challenges which the modern e-commerce industry faces today.

Most e-commerce and retail companies achieve their targets by leveraging the power of data and boosting sales by implementing search and recommender systems on their websites. With the above mentioned new upcoming display trends and huge increment of the online traffic volume, two fundamental challenges have to be solved. First, we need to design a model framework to facilitate an effective semantic understanding, search, and retrieval of images and videos, so that we can recall and rank products with their appropriate multimodal contents. This can help consumers make better decisions as well as delve more into the platforms with great potential. Second, machine learning systems are prone to exploitation if equipped with short-term goals, e.g., ctr, cvr or gmv, and the direct effects would cause severe Matthew's effects where only very small proportion of items from different sellers get exposed to online users. Thus, understanding whether the systems are fair is crucial and has deep influence on the development of the e-commerce platforms. To help tackle these challenges and further nourish the development in this field, we propose the following two competing tasks, recall for multi-modal entities and debiasing, as detailed below.


2. Schedule

30th March, 2020: Sample set of the training data released and open registration.

7th April, 2020: Entire training and validation data released.

13rd April, 2020: The (unlabeled) test set A released (for development only, not taken into account when deciding the final winning solutions).

27th May, 2020: Registration deadline.

4th June, 2020: The (unlabeled) test set B released for final submission.

11th June, 2020: Submission ends.

15th June, 2020: Deadline for submitting the technical report and code.

20th June, 2020: Challenge award notification.

23rd - 27th August, 2020: KDD conference.

All deadlines are at 11:59 PM UTC on the corresponding day. The organizers reserve the right to update the contest timeline if necessary.


3. Registration to the Competition

  • Registration time: from March 30, 2020 to May 27, 2020 UTC. The registration entrance will be closed and team change will be disabled at 11:59 PM on May 27, 2020 UTC.

  • The competition is open to all individuals, companies, colleges, research institutions. One account per participant. A contestant can ONLY join one team. The registration information must be correct and valid. Any false information or cheating behavior will lead to disqualification for ranking and awarding.

  • Members of Alibaba Group can participate in the Competition, but are excluded from the Awards. Advisory board members (and their immediate families and members of the same household) of the Competition Sponsor, Tianchi and their respective affiliates, subsidiaries, contractors, agents, judges and advertising and promotion agencies are not eligible to participate in the Competition.

  • Registration method: Contestants can login Tianchi platform with the Alibaba Cloud account. Click one of the following links for registration of Alibaba Cloud: International Site, 中国站, Japanese Site. For Japanses Site users, if you have trouble when you login, this post may help.


4. Awards

1st Place: $8,000
2nd Place: $4,000
3rd Place: $2,000
4th to 10th Place: $500 for each

Members of the top 20 teams will have the opportunity to deliver their resumes directly to us through the green channel and be prioritized for the Alibaba campus recruitment. Please contact the email (kdd_cup@alibaba-inc.com) for more details and send your resume to us!


5. Rules and Notifications

5.1. Rules

  • For this competition, we prepare the test set A and test set B. The test set A is released earlier and used to improve the model. The final rank and score will be determined by the evaluation on test set B ONLY.

  • Each participating user/group may submit up to 3 times per day for test set A and 1 time per day for the final test set B.

  • Before 4th June, the evaluation results on test set A will be ranked and displayed on the public leaderboard. The leaderboard updates daily at 10AM PT. From 4th June to 11th June, the score and rank on test set B will NOT be provided until submission ends. After all evaluations on test set B are finished, the leaderboard will update the final ranks and scores.

  • One account per one participant. You cannot sign up to Tianchi from multiple accounts and therefore you cannot submit from multiple accounts.

  • It's not allowed to merge teams after registration deadline . Please confirm the members of your team before the registration deadline.

  • Sharing code privately outside of teams is not allowed.

  • Participants are restricted to train their algorithms on the datasets provided by the organizers. Any external data for trainng is NOT allowed.

  • We ask that you respect the spirit of the competition and do not cheat. Hand-labeling is forbidden.

5.2. Notifications

  • Top 20 teams should submit a technical report that includes a summary of their submission (suggested length 1-4 pages), as well as the code for reproducing the results (see the page on code style for more details). Only effective submission will be considered any awards and will be put in the final leaderboard of the competition.

6. About

Contact

If you have any questions, please contact kdd_cup@alibaba-inc.com

Organizer

![enter image description here](https://tianchi-public.oss-cn-hangzhou.aliyuncs.com/public/files/forum/158574586319968791585745862816.png =600x)