Tech Blog Archive

Machine Learning in Research

Mathesis: Elements of Learning and Intelligence

A formal and interdisciplinary theory of learning and intelligence that combines biology, neuroscience, computer science, engineering and various branches of mathematics to provide a unifying framework, direction and a broader horizon for neural network and machine learning research.

By: John (Ioannis) A. Drakopoulos, Principal Applied Researcher
Machine Learning in Research

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.

By: Senthil Padmanabhan
Android in Product

eBay’s Image Clean-Up Feature Brings the Power of Image Processing Algorithms to Android

This feature enables our sellers to create cleaner listings.

By: Dzmitry Lebedzeu, Software Engineer
Search Science in Product

eBay Makes Search More Efficient Through Personalization

eBay introduces Best Match to personalize buyers’ search feeds.

By: Shreya Raval
Platforms and Frameworks in Engineering

Streamlining Language Technology from Idea to Deployment

In recent eBay Tech Blog articles, we presented the Unified AI platform called Krylov and our pythonic tool to interact with the platform, PyKrylov. In this article, we introduce our Natural Language Processing framework built on top of the AI platform.

By: Daniel Stein, Gregor Leusch, Praseeda Sathaye and Selcuk Kopru
Machine Learning in Product

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.

By: Senthil Padmanabhan
Computer Vision in Research

A Human-centric Approach for Evaluating Visual Search Models

Part of our mission within Core AI at eBay is to develop computer vision models that will power innovative and compelling customer experiences. But how can we compare several visual search models and say which of them works better? This article will describe a method that is tackling this problem directly from the eyes of the users.

By: Michal Romi, Michael Ebin and Chantal Acacio
Machine Learning in Engineering

PyKrylov: Accelerating Machine Learning Research at eBay

A recent eBay Tech Blog article1 presented the Unified AI platform called Krylov. In this article, we show how Krylov users interact with the platform to build and manage powerful workflows in a pythonic and efficient way.

By: Selcuk Kopru and Jingjing Jiang
Machine Learning in Engineering

eBay’s Transformation to a Modern AI Platform

How the AI transformation at eBay was powered by a modern AI platform with a unified and open approach.

By: Sanjeev Katariya and Ashok Ramani
Service Architecture in Research

eBay’s New Approach to Managing a Vast Service Architecture

Learn how eBay's architecture knowledge graph was developed; the benefits eBay has received from it; and the use cases we see now and in the future for this approach.

By: Hanzhang Wang, Chirag Shah and Sanjeev Katariya
Agile in Research

Towards Agile AI

In this article, we propose a set of better practices, designed by and for eBay ML scientists, for facilitating weaving ML modeling into the cyclical Agile process flow.

By: Jean-David Ruvini
Machine Learning in Research

Building a Product Catalog: eBay's University Machine Learning Competition

Trade has played a critical role in the history of humanity and yet, data from ecommerce, the modern form of trading, has received limited attention from academia. We at eBay want to change that.

By: Senthil Padmanabhan
Performance Engineering in Engineering

eBay's Hyperscale Platforms

In the era of artificial intelligence, machine learning, and cloud technology, data is growing exponentially. eBay data continues to grow, serving more than 182 million buyers and $13.4 billion of transactions completed on mobile devices. Understanding how to manage data is a key to success. System hardware platforms must be designed for the data.

By: Lam Dong
Machine Translation in Research

Going the Distance — Edit Distance 3

How do you normalize Edit Distance? Some simple ideas to get useful numbers about the changes in your text.

By: Silvio Picinini
Machine Translation in Research

Going the Distance — Edit Distance 2

If you change a sentence, should you see the characters or words that changed? Edit Distance is back to help you figure this out.

By: Silvio Picinini
Machine Translation in Research

Going the Distance — Edit Distance 1

What is Edit Distance? How could it be used to measure quality? Find out the basics about this simple metric used for Machine Translation.

By: Silvio Picinini
Computer Vision in Product

eBay Makes Visual Shopping More Intuitive While You Browse

Our newest experience helps you find more products you just can't describe.

By: Jonathan Chard
Machine Learning in Engineering

eBay’s Platform is Powered by AI and Fueled by Customer Input

Artificial intelligence is woven into all aspects of eBay’s platform, inspiring economic empowerment and enhanced experiences.

By: Sanjeev Katariya, VP & Chief Architect, eBay AI and Platform, eBay
Deep Learning in Engineering

Complementary Item Recommendations at eBay Scale

Generating relevant complementary item recommendations that drive conversion at eBay is a challenging problem. In this blog post, we describe some of these challenges, and how we incorporated several different signals, including behavior-based (co-purchase, co-view, co-search, popularity) and content-based (title text), to significantly enrich the number and quality of candidate recommendations. This can produce an improved user shopping experience, which can lead to increased transactions between eBay buyers and sellers, and an increase in the number of items bought, which is good for the eBay marketplace as a whole.

By: Yuri M. Brovman
Deep Learning in Research

Explainable Reasoning over Knowledge Graphs for Recommendation

Incorporating knowledge graphs into recommender systems has attracted increasing attention in recent years. By exploring the interlinks within a knowledge graph, the connectivity between users and items can be discovered as paths, which provide rich and complementary information to user-item interactions. Such connectivity not only reveals the semantics of entities and relations, but also helps to comprehend a user’s interest. However, existing efforts have not fully explored this connectivity to infer user preferences, especially in terms of modeling the sequential dependencies within and holistic semantics of a path. We have developed a new model named Knowledge-aware Path Recurrent Network (KPRN) to exploit knowledge graphs for recommendation.

By: Dingxian Wang, Canran Xu, Hua Yang and Xiaoyuan Wu
Computer Vision in Research

Interactive Visual Search

Interactive visual search with user feedback helps buyers find the perfect item and while enjoying the exploratory journey.

By: M. Hadi Kiapour, Shuai (Kyle) Zheng and Robinson Piramuthu
Computer Vision in Research

Seven Tips for Visual Search at Scale

We present seven tips for visual search at scale, based on our KDD 2017 paper titled "Visual Search at eBay."

By: Fan Yang, M. Hadi Kiapour, Robinson Piramuthu and Qiaosong Wang
Computer Vision in Research

Beyond Logos and Patterns: How We’re Training eBay’s AI to Understand Brands

We’re researching how to recognize brands using computer vision by training our AI to look beyond logos and iconic patterns.

By: M. Hadi Kiapour and Robinson Piramuthu
Computer Vision in Research

ModaNet: A Large-scale Street Fashion Dataset with Polygon Annotations

Searching for an ideal dress or pair of shoes sometimes could be challenging, especially when you do not know the best keywords to describe what you are looking for. Luckily, the emerging smart mobile devices provide an efficient and convenient way to capture those products of interest in your photo album. The next natural thing is letting an ecommerce app like eBay figure it out for you.

By: Shuai (Kyle) Zheng, Fan Yang, M. Hadi Kiapour and Robinson Piramuthu
Computer Vision in Product

Drag and Drop Search: A New Way to Search on eBay

eBay has over a billion listings across a wide variety of categories that millions of buyers search every day. It is a significant challenge to connect the right buyer to the right listing and in the process to present the user with similar items that are suited to the buyers inputs.

By: Ravi Pitapurapu
Computer Vision in Product

Love It? Find More Like It with eBay’s New Image Search Feature

Our latest visual shopping feature helps you discover more items that look like your favorites with only the swipe of a finger.

By: Seema Jethani and Venkat Medapati
Computer Vision in Engineering

Large-Scale Product Image Recognition with Cloud TPUs

Customers all over the world use eBay to buy and sell all kinds of products. With more than one billion product listings on eBay, it is essential for eBay to use cutting-edge AI to help everyone find the products that they want. And visual search is increasingly important—with cameras on every smartphone, eBay customers want to be able to snap a photo to find exactly what they see.

By: Shuai (Kyle) Zheng
Testing in Research

GUI Testing Powered by Deep Learning

Deep Learning (DL) is revolutionizing the face of many industries these days, such as computer vision, natural language processing, and machine translation, and it penetrates many science-driven products and technological companies, including eBay. These days, DL is taking its first strides in eBay’s Quality Engineering (QE) space, and it has already proven to outperform the best test veteran and industry-grade applications one could find.

By: Yotam Sharan, Honghao Wang and Sovan Rath
Bots in Engineering

Altus Care: Applying a Chatbot to eBay Platform Engineering

eBay developers recently combined several commonly used technologies, including Lucene search and the Stanford Natural Language Processor, to create Altus Care, a chatbot that provides an instant one-stop support solution for internal eBay Altus users.

By: Alison Shu
Search Science in Research

Finding Desirable Items in eBay Search by a Deep Dive into Skipped Items

When you search on eBay and there are many matching listings, how does eBay figure out which ones to rank at the top? One key ingredient is to determine how well the listing matches the intent of the query.

By: Ishita Khan