eBay 2022 University Machine Learning Competition

Liz Morton
Liz Morton


UPDATE: 1-12-23

eBay has announced the winner of the 4th Annual University Challenge.

eBay Announces Winners of 4th Annual Machine Learning Challenge
Using the power of natural language understanding, these two students created fantastic solutions.

eBay’s annual Machine Learning Challenge for University Students is one way that the company finds bright young minds in the fields of engineering and technology. Students are tasked with a thorny problem — last year, it was predicting shipping times — and the finest solutions find their creators rewarded with an internship.

This year, applicants were given the challenge of building a model that can accurately extract and label the named entities in the dataset of item titles on eBay. Those “named entities” might include brands, locations, styles, product names, colors, materials, sizes, and other semantic strings, words and phrases that can help classify an item. Using Named Entity Recognition (NER), a machine learning process that automatically susses out these categories, our applicants tackled the very real-world challenge any ecommerce platform faces: how do we extract structured data from unstructured sources like listings?

A whopping 591 teams entered this year, and we’re thrilled to announce the two winners of this year’s challenge: Rupashi Sangal and Sanjayan Pradeep Kumar Sreekala, both currently studying at the University of California, San Diego. “The problem statement caught our attention, and the opportunity to work with a real-world dataset, implement various models, and explore their results was very appealing, so we decided to participate in the competition,” says Rupashi. Their solution “utilized one of the largest and latest state-of-the-art BERT models, called Deberta V3, from Microsoft,” says Rupashi. “To improve the performance of our model, we also employed K-fold cross-validation and ensembling techniques.”

Rupashi, who is a first-year Masters student studying electrical and computer engineering with a specialization in machine learning and data science, was previously a software engineer in India. “I aspire to become a solutions architect in AI and work towards creating innovative and trendsetting AI-powered applications,” says Rupashi — and we hope we can help her along that journey.

Sanjayan notes that the Machine Learning Challenge posed “a fun opportunity to test our skills and gain valuable experience.” He is currently studying computer science and transitioning his career to focus more on machine learning. Like Rupashi, he previously worked in industry in India, in Sanjayan’s case as a digital design engineer.

Both Rupashi and Sanjayan have accepted internships with eBay’s Structured Data Applied Research team in San Jose, for the summer of 2023. “I am excited to gain practical experience with machine learning systems in production environments and learn about best practices for deployment and maintenance,” says Sanjayan. We’re excited, too — to have such bright minds here at eBay.

eBay has announced its 4th Annual Machine Learning University Challenge with this year's focus on extracting relevant product data from listing titles.

eBay is pleased to announce its 4th Annual University Challenge in the space of Machine Learning on an e-commerce dataset...

...As in the last three years, the prize for this year’s winners will be a summer internship with eBay (this time for the 2023 summer) .

The problem we invite you to consider for this year is to build a model that can accurately extract and label the named entities in the dataset of item titles on eBay. Named Entities are the semantic strings/words/phrases that refer to people, brands, organizations, locations, styles, materials, patterns, product names, units of measure, clothing sizes, etc.

It's always interesting to see what problems eBay sets out for these young minds to solve, revealing areas where the tech-led reimagination of the company may be focusing next.

In past competitions, eBay asked students to help more accurately predict shipping delivery dates and grapple with structured data challenges like how to identify two or more listings as being for the same product by putting them into the same group.

eBay’s 3rd University Machine Learning Competition: Predicting Shipping Delivery Dates
For our annual ML competition, we challenged university students to predict how many days a carrier takes to deliver packages.
Building a Product Catalog: eBay’s 2nd Annual University Machine Learning Competition
Participating universities will structure listing data to help solve a real-world ecommerce challenge.
Building a Product Catalog: What we Learned from our University Machine Learning Competition
We challenged more than 100 college students at seven universities to structure listing data using AI and machine learning.

As in past years, the prize students are competing for a summer internship at eBay, with this year's winners taking a spot in the summer 2023 internship program.

eBay’s internship program is a combination of real work experience plus a robust program giving interns exposure to various business verticals, executives and networking opportunities. The internship will also be an excellent opportunity for students to put their ML models into real use.

If you were running eBay's University Machine Learning Competition, what would be your top challenge for these students to solve? Let us know in the comments below!

My personal pick would be to use machine learning to identify and remove scam listings/flag hijacked accounts used for fraud based on common image and listing attributes - I'll even give them one brown 1974 Audi as a head start. 😉

Why Doesn’t eBay Do More To Stop Car Scams?
It seems like eBay car scams have been around forever, why doesn’t eBay do more to curb this particular kind of fraud?

Liz Morton Twitter

Liz Morton is a seasoned ecommerce pro with 17 years of experience in online sales & marketplaces, providing expert commentary, analysis & news about eBay, Amazon, Etsy & more at Value Added Resource!