Goodreads has acquired Discovereads.com, a company that provides algorithmic book recommendations. With Discovereads technology, Goodreads will plumb its database of 100 million book ratings from 4.6 million users to find patterns in the kinds of books people read and to generate personalized recommendations. Originally built to help readers find new books based on what their friends are reading, the company will add another book discovery tool with a Netflix-style algorithm.
This move puts Goodreads in a position to compete with Amazon. "Until now, Amazon was the only source of algorithmic book recommendations of any quality," says Discovereads CEO and soon to be VP of Goodreads Business Development, Kyusik Chung. "But their recommendations are hampered because they usually don't have a long list of ratings from any individual to gain a deep understanding of what books he or she likes. Goodreads doesn't have that problem—their dataset per person is rich and deep, and we will be able to build some really amazing experiences with it."
Book discoverability has become an increasingly difficult problem for readers. More than 300,000 books will be published this year, and the rise of ebooks has flooded the market with self-published authors. “We have so much data on what people read, but we've never built algorithmic recommendations because it's a really, really, hard problem to get right, ” says Goodreads CEO Otis Chandler. “We're excited to have the Discovereads team onboard, because they are experts in machine learning algorithms."
Inspired by the Netflix prize (and with some direct help from a member of second place team), Discovereads Chief Technology Officer, Brian Percival, left his PhD at Stanford University in Electrical Engineering (in neural circuitry software modeling) to pursue this project. The company has taken three years to refine the technology to a precise level. The Discovereads technology combines multiple machine learning algorithms and graph analysis techniques to analyze book ratings and spot trends. Goodreads expects to have Discovereads fully integrated within the next three months.
The Discovereads technology will also improve Goodreads’ unique targeted advertising program. Authors and publishers can purchase ads for their books and target the ads to members who have read similar genres. All six of the major publishers actively work with Goodreads to promote their books, and authors such as James Patterson, Neil Gaiman, Paulo Coelho, Richelle Mead, Cassandra Clare, Margaret Atwood, and 17,000 more authors have signed up on Goodreads to collect fans and publicize their work. The new technology will make it more likely that readers will see sponsored books that they will enjoy.
Goodreads (goodreads.com) is the largest social network for book lovers in the world with over 4.6 million registered users and 75 million monthly pageviews. Members can see what their friends are reading, join book clubs, recommend books, and track and discuss the books they're currently enjoying. The Goodreads monthly newsletter (4 million circulation) includes author interviews, recommendation lists, literary charities, author Q&As, and more. In addition, members receive a monthly new releases mailer that is personalized to each user, letting them know which new books by authors they have read are available each month. Goodreads is committed to keeping the joy of reading alive.