Fashion Recommendations Challenge

by FARFETCH for ECML PKDD 2021


About

The importance of online sales in the luxury fashion space has been growing at an accelerated pace in the last few years, as consumers of this once traditional industry now expect easy access to a worldwide network of brands and retailers. FARFETCH operates in this space and has the mission to bring together creators, curators, and consumers of fashion, all over the world.

To be successful in this landscape, it's necessary to provide a tailored, personalised and authoritative fashion shopping experience. Recommendation systems play an important role in the user journey, allowing customers to discover products that speak to their style, complement their choices, or challenge them with bold new ideas. FARFETCH continuously works to improve its own recommender system with this ambitious goal in mind.

In this challenge, you will attempt to solve this problem by building your own recommendations algorithms while working with a real-world dataset.

Learn more about our system in the series of blog posts: How to build a recommender system: it’s all about rocket science - Part I and Part II .

Participation & Data

The FARFETCH Fashion Recommendations Challenge dataset is a large sample of FARFETCH's recommendations system impressions and associated click events, captured over a period of 2 months. The goal of the competition is to predict which of the products that were shown to a user lead to an actual click, based on known historical labelled interactions.

The dataset comprises over 5.000.000 recommendation events, 450.000 products and 230.000 unique users. It represents real, unbiased, but anonymised, interactions of actual users of the FARFETCH platform.

The challenge ended on July 1st and the dataset is no longer publicly available. 104 teams registered to participate, and we have received over 300 submissions during the whole competition!

Final Standings

RankTeamMRR
1Second Life0.52571
2DeepBlue0.49031
3densityRecs0.47407
4user0.47013
5Data Clube0.46793
6allmightyML0.46585
7POLSL Team0.44691
8UFSJ0.44681
9Space Red Squirrel0.44262
10Baseline0.43864

Congratulations to Manish Pathak and his team, Second Life, the winners of the FARFETCH Fashion Recommendations Challenge!

Timeline

April 1, 2021 Challenge starts

Submissions open. Train and validation datasets are made available to the participants. Teams can make multiple submissions every day and track their performance on the public leaderboard.

June 24, 2021 Final Phase begins

Test dataset is made available to the participants. Teams can now make their final submissions, with results hidden until the final announcement.

July 1, 2021 Challenge ends

All submissions closed. The committee will evaluate the submissions and determine if they are compliant with the competition rules. The winners are decided according to the performance in the chosen metric.

July 5, 2021 Challenge results

Winners are notified and prizes are awarded. Results are published to the general public.

July 22, 2021 Paper submissions due

Prize

Each element of the winning team, up to a maximum of 6, will be awarded €150 of FARFETCH credit, to spend freely on FARFETCH.COM or on the FARFETCH App.

Organizers

  • Diogo Gonçalves, FARFETCH
  • Isabel Chaves, FARFETCH
  • João Gomes, FARFETCH
  • Pedro Nogueira, FARFETCH
  • Tiago Otto, FARFETCH
  • Vanessa Marinho, FARFETCH

For more information, contact us at [email protected].