Press Release: Leading EBook Subscription Service Refines Overall Web Experience for Customers
WILMINGTON, NC, October 17, 2014 - With thousands of published and independent authors to sort through, many eBook subscribers grow frustrated searching through the avalanche of titles available to them. Well, Entitle Books, a fast-growing monthly eBook subscription service where customers actually own the books they download, has the answer to book lovers' prayers thanks to two strong recommendation features: "If These Books Had a Baby" and "Recommendation Station."
Through intricate data mining and advanced machine learning algorithms, Entitle Books quickly and easily learns what subscribers are interested in so they spend more time reading and less time searching. Best of all, the more subscribers interact with the site and app, the more precise the recommendations become making it more like a personal librarian than a technological marvel.
"Subscribers absolutely love our recommendation function and given the talent and effort behind its creation, they have every right to do so," said Bryan Batten, Founder and CEO of Entitle Books. "What's truly innovative about our system is the speed at which it learns your preferences and the high level of personalization it achieves so that over a short period of time, you are getting recommendations that are ideal for you."
Entitle Books partnered with Nicholas Ampazis, a tenured assistant professor at the renowned University of the Aegean and one of the brightest minds in deep data mining and machine learning to develop a best in class recommendation platform that gets "smarter" the more it is used. Ampazis was part of the Ensemble Team that tied for first in the Netflix Prize, an international competition held by the streaming media giant to improve its search functionality.
Adds Ampazis: "Entitle Books is a paradise for recommendations because they have two very well-defined sources of information: the actual text that is contained in the books, and the star ratings given to each book by the consumer. When we apply our proprietary text mining methods with the collaborative filtering / machine learning methods, the result is a continually refined and extremely insightful recommendation list."