Pinterest head of engineering Michael Lopp wrote in a blog post:
Over the past year, Kosei has been building a unique technology stack that drives commerce by making highly personalized and powerful product recommendations, as well as creating a system that contains more than 400 million relationships between products. As we build a discovery engine for all objects, Kosei is a perfect fit for our team.
Acquiring Kosei makes incredible sense for Pinterest. As the company has turned much of its attention toward its discovery and search engines to help users find even more content, plugging its paid content into those results is critical.
In April, Pinterest took a big step toward becoming an image search engine with the launch of Guided Search, a predictive search capability that serves results related to a user’s search query even with just the first few letters. It also announced that it will boost its Related Pin coverage to include more than 90 percent of the pins in its network.
Then in May, it finally launched its long-awaited first revenue stream, Promoted Pins, which show up in its search and category feeds.
Kosei’s machine learning technology and recommendation engine could help further bridge the two.
Kosei was founded in 2014 by Lance Riedel and Jure Leskovec, and is based in Palo Alto, California. It has a team of seven, according to its website.