How does eBay, which recorded more than 6.7 million sellers and approximately 179 million active users spread out across 190 markets by the close of 2018, leverage AI in delivering excellent seller and buyer experiences?
Mainly through supplying structure to over 1.2 billion listings that the company’s users engage with each day.
In a recently published blog post, eBay pointed out the numerous ways it is leveraging machine learning to inspire “economic empowerment” and “enhance experiences” across its ever-changing marketplace.
Two Decades of Data
eBay has over two decades worth of useful data that helps in fueling its natural language processing (NLP), machine translation, computer vision, recommendation, and personalization algorithms, which are at the core of the company’s discovery and purchasing funnels.
“Artificial intelligence touches every experience within eBay,” writes Sanjeev Katariya, VP and chief architect of AI and platforms at eBay.
“It is woven into all aspects of the eBay marketplace, anticipating the needs and wants of buyers and sellers, inspiring shoppers on the hunt for something special, empowering entrepreneurs looking to grow their business and making the platform more accessible to everyone.
Over the last few years, we’ve worked to make our shopping experience more relevant to every shopper’s needs, whether customers are looking to discover, be inspired, find a specific item, or browse.”
Interests, a module featured on eBay’s homepage, tries to figure out shoppers’ styles, hobbies, passions, and leverages the gathered insights in coming up with personalized product recommendations.
eBay said that over 2.6 million individuals in five nations who leverage Interests get an average of 18 product recommendations on the company’s smartphone application and about 10 on the web page.
The company’s search improvements corresponded with the release of Interests.
Natural Language Processing NLP and Search
According to eBay, it uses artificial intelligence in better understanding areas like natural language and units of measurement.
As such, a simple search for “watches,” for example, will show a wide variety of movement types, materials, prices, and brands.
According to eBay, computer vision has played a considerable function in the shopping flow.
Late 2016 witnessed the rolling out of Find it On eBay, which shows product listings similar to those available on almost all webpages, and Image Search, which allows users to locate items through taking photos of existing objects
“All of these improvements use AI to power a sharper experience for our buyers,” eBay says. “We have a better understanding of who our shoppers are, what they might be looking for, and how they want to shop.”
Shoppers are not the only ones who have benefited greatly from the adoption of machine learning by eBay.
In fact, the company claims that advanced natural language processing (NLP) algorithms have allowed it to expedite listing times through improving searches in a bid to identify the best-matched products.
AI and Translation
eBay also says its translation work has significantly reduced the time taken to process international clients.
A given study revealed that English-to-Spanish AI-driven translation on eBay boosted exports by 17.5%.
The company also claims to have improved guest onboarding through halving the steps involved in purchasing a particular product.
eBay also believes that its latest product-based shopping models assist many buyers in finding items more quickly.
“We used open source technology to build an in-house AI platform that reaches across eBay to enable collaboration and training of our AI models at scale.
It allows our data scientists and engineers to experiment, build products and experiences for customers, and leverage AI at scale,” Katariya writes.
“While we’ve elevated the experience for our customers with AI for more than a decade, the recent advances in deep learning have … enabled us to scale to larger and more complex data sets [consisting of] billions of data points and [to approach] human-level competency [with deep learning models].”
Artificial intelligence forms just a single section of the $4.88 trillion e-commerce space. As a result, eBay has in recent times unveiled a selection of APIs intended for machine translation, its marketplace, and image search, which it offers to developers based at partner sites free of charge.
Ebay’s AI Across the Whole Supply Chain
Individually, the company has applied domain science to challenges such as shipping times, trust, and risk, as well as investigated ways of enhancing artificial intelligence (AI) models in deployment and minimize bias.
Ebay is undeniably doing an excellent job.
In fact, in the last quarter of 2018, the company generated a net income of 763 million dollars, surpassing the losses made a year-ago of $2.6 billion.
The Vice President of Applied Research at eBay Tom Pinckney told VentureBeat that artificial intelligence was driving “north of $1 billion per quarter” in growing marketplace sales.
“Our approach allows us to determine what methods work and at what time so that we can create these meaningful experiences for our buyers and sellers,” Katariya writes.
“eBay is a robust marketplace, and AI is at the center of that journey, positioning the platform as a leading intelligent marketplace, and we’ll never stop aiming for the best customer experience.
Looking ahead, we will continue down the path of innovation through eBay’s AI managed marketplace, knowing that the scope of what’s possible with AI expands every day.”
eBay is a US-based global e-commerce company located in San Jose, California that promotes business-to-consumer and consumer-to-consumer sales through its webpage.
Since its inception back in 1995 by founder Pierre Omidyar, the company has grown into a multibillion-dollar enterprise with numerous operations spread out across 30 nations globally.
eBay manages its website, an online shopping and auction site in which businesses and individuals sell a broad range of commodities globally.
Although the eBay website does not charge buyers, sellers have to pay a certain fee for listing their products on the site after they exhaust the provided limited free listings, and then after they sell their items.
Over the years, eBay has acquired several companies including PayPal, Skype Technologies, StubHub, visual search engine Corrigon, Qoo10.jp, and owns about 25% of classified listings site Craigslist.
With approximately 14,100 employees as of December 2017, eBay has several subsidiaries including Marktplaats.nl, G-Market, iBazar, StubHub, Gumtree, Auction Co., Kijiji, GittiGidiyor,Half.com, and eBay Classifieds just to mention a few.