What You Will Read Next
Skip other details (including permanent urls, DOI, citation information): This work is protected by copyright and may be linked to without seeking permission. Permission must be received for subsequent distribution in print or electronically. Please contact mpub-help@umich.edu for more information.
For more information, read Michigan Publishing's access and usage policy.
Abstract
Predictive analytics plays a crucial role in modern web applications. The next movie you watch on Netflix or song you listen to on Spotify may be the result of a recommendation algorithm driven by predictive analytics. In this talk, we’ll explain how we’re using data at Safari to suggest better content for our readers. Using predictive analytics, we can guess what a reader will want to read next based on a number of factors, including related content, time of day, geographic information, and much more. Beyond the technical implementation of a recommendation engine, we’re interested in the questions predictive analytics raises (and answers) around content consumption, curation, and creation. What makes a book or video more or less engaging? What keeps readers reading (and viewers watching)? What does a paying customer read versus a reader in a free trial period? As we find the answers to these questions and share them with our publishing partners, how will that data influence editorial strategy around the development of new content?
