On Friday, eBay, which has reported adjusted earnings per share of 47 cents on revenue of $2.1 billion in Q1, announced the completion of its acquisition of Israeli startup SalesPredict, which leverages advanced analytics to predict customer buying behavior and sales conversion. SalesPredict will support eBay’s artificial intelligence, machine learning and data science efforts, and their deep expertise will contribute to eBay’s structured data efforts.
Upon the close of the transaction, a number of SalesPredict’s employees will join eBay’s structured data organization, working from eBay’s Israeli Development Center in Netanya. SalesPredict Co-Founder and CEO Yaron Zakai-Or will serve as a Director of Product Management, Technology, and SalesPredict Co-Founder and CTO Kira Radinsky will be Director of Data Science & Chief Scientist, eBay Israel.
SalesPredict was co-founded in 2012 by Zakai-Or and Radinsky and its main investors include Yandex, AfterDox, Redline Capital, KGC Capital, and Pitango Venture Capital.
Dr. Kira Radinsky, who immigrated to Israel from Russia at age 4, says her passion “has always been, and always will be, predictions.” During her PhD studies and her work in Microsoft Research she was leading research in the field of Web Dynamics and Temporal Information Retrieval. She developed algorithms that “leverage web knowledge and dynamics to predict future events, that enable early warning of globally impactful events (e.g. riots or diseases) by spotting clues in past and present news reports.”
One of the best examples of Radinsky’s ability to predict future events was her warnings about violent riots in the Sudan during the Arab Spring. “We noticed a pattern that repeats in countries where the people are poor but the land is rich in resources—like the Sudan,” Radinsky told The Marker last week. “We noted that in such countries the canceling of state subsidies starts riots among students, and if the spiraling down isn’t stopped, things may end up in violent clashes.”
“At that time, when it was known that gas subsidies were being removed in the Sudan, our system had already issued an alert for a high chance of riots there. And, indeed, the riots began with student demonstrations, and turned into clashes with police and many protesters being hurt,” Radinsky continued. She said their system had also pointed to a similar pattern in Egypt, when bread subsidies were removed, but at the time there wasn’t enough data for the system to work with and it didn’t predict the downfall of President Mubarak.
“We lead the predictive marketing industry and strive to build the next generation business operating system,” Radinsky wrote on her Technion web page. “I am passionate about our vision of ‘Automatic Data Science’: an on-going effort to create a product that is completely automated without the need for an expert in the loop.”
“Today’s agreement to acquire SalesPredict builds upon our recently completed acquisition of Expertmaker, marking another milestone for eBay in our plans to apply world class learning approaches to building the world’s most comprehensive product catalog and pricing guide,” said Amit Menipaz, Vice President and General Manager of Structured Data at eBay. “SalesPredict’s deep expertise in predictive analytics and machine learning will contribute to eBay’s structured data efforts. For our buyers, it will help us better understand the price differentiating attributes of our products, and, for our sellers, it will help us build out the predictive models that can define the probability of selling a given product, at a given price over time.
There are three key efforts that comprise eBay’s structured data initiative: collect the data; process and enrich the data; and create product experiences. SalesPredict will contribute to data processing and enrichment, specifically with respect to inventory insights.
“With more than 900 million listings on eBay, there is an enormous opportunity to extend our experience in machine learning and predictive analytics to help eBay identify important product attributes that can affect the price of a product,” said Yaron Zakai-Or. “In partnership with eBay’s broader structured data team, we will help arm eBay sellers with more information about the value of items, ultimately helping to increase customer sales conversions.”
“As a data scientist at heart, I’ve always been interested in exploring the myriad ways we can leverage data to predict future high impact events,” said Kira Radinsky. “In founding SalesPredict, our vision was to bring about a major change in how business is conducted by unifying micro- and macro-economic predictions. Today, this vision has yielded state-of-the-art automated data science capabilities. I am excited to have the opportunity to bring these capabilities to eBay’s community and ecosystem.”