Discovereads is the best place to discover books you'll love.
Are you fed up with false promises of personalized recommendations? Did you tell other sites that you liked a fantasy novel, only to have them assume you like all fantasy novels? Or did they assume that your tastes are identical to those of your friends, even though you find your friends interesting because they're different? Unlike other book social networks, Discovereads doesn't just show you a list of the most popular books. We know that your tastes are unique and you probably don't need our help to find out about the most popular best sellers.
Our mission is to help you discover books that you'll love, but might not find on your own - books that fit your personal interests and your tastes, because many people disagree about which books on a topic are the best.
We're kind of like Pandora for books. We learn your personal tastes and help you explore. You rate books and we make better recommendations for you. In addition, we help you tap into your network of friends, and we provide filtering tools to discover the gems you'll pass on to your friends.
How we make better recommendations
Discovereads' Taste Engine compares how you rate books with how everyone
else rates books. When it analyzes the data, it finds ways in which you are
similar to someone else and ways in which you are different. It builds a web
of relationships between users and books and uses an array of algorithms
(sometimes different algorithms work better for different users or books) to
learn each person's tastes.
(If you're a machine-learning whiz who likes to geek out on RSVDs, RBMs,
KNNs, and GNLRs, drop us a line - we'd
love to chat!)
Once the Taste Engine has learned your tastes, it predicts how much you will like books you haven't yet rated. These predicted ratings (shown in orange) are unique to you and your tastes - they may vary widely from the predicted ratings for your friend, reflecting your different tastes.
Next, the Taste Engine combines that with a knowledge of the topics or genres you show most interest in to recommend books that you'll enjoy. If you happen to be viewing one of your reading lists, it makes recommendations based on the books in that reading list.
Every time you rate a book or add a book to a reading list, the Taste Engine learns a little bit more about your personal tastes. In just a couple of minutes, it recalculates its recommendations for you. So, the more books you rate, the better Discovereads understands your tastes, and the better the recommendations we are able to provide.
How you get better recommendations from your friends
It's not just about the personalized recommendations Discovereads provides. Who knows you better than your friends? We make it really easy for friends to recommend books to you. All of your friends will see those recommendations in their news feeds and will be able to weigh in as well, so you get the advice and input from all of your friends, not just one.
So go ahead and invite your friends. We know you already like talking about which books to read next. Recommending on Discovereads takes it a step further.
The Discovereads Team
-
Librarian
Kyusik likes non-fiction books that investigate the economics behind how our world works and books about crazy mountaineering adventures. He's not a big fan of "pseudo-science" books or most of the recent hyper-popular novels. He looks forward to his daily commute, when he gets most of his reading done.
Prior to founding Discovereads, Kyusik was a Product Manager at Zillow.com where he helped create the "Zestimate" valuation engine that predicts over 45 million individual home prices every day. Prior to Zillow, Kyusik was a Lead Program Manager at Expedia.
-
Reading now:
-
Recently enjoyed:
-
-
Librarian
Brian is an Electrical Engineering PhD student at Stanford, but put that on hold to build Discovereads. His research interests include neural modeling in software and hardware, and of late, machine learning algorithms and recommendation systems. Before Stanford, Brian spent six years at Sapient architecting enterprise applications in the financial, energy and government sectors.
Brian splits his reading fairly evenly between fiction and non-fiction. In fiction, he likes primarily literature and humor (though he recently broke down and started devouring the Harry Potters), while his non-fiction tastes vary widely, though geekana (e.g. The Cuckoo's Egg, Gödel, Escher, Bach ), popular science (Kyusik would say "pseudo-science") ( The Code Book, The Third Chimpanzee ), and Wall Street (try reading The Age of Turbulence with a straight face now!, Liar's Poker ) are a few threads that run through his reading resume.
Brian has been disappointed with his book social network site experience. If his friends weren't writing lots of reviews, he wasn't discovering new books to read. He's strongly committed to helping readers find books they'll love whether their friends are reading them or not!
-
Reading now:
-
Recently enjoyed:
-
Contact Us
We've embarked on a journey - a quest to improve the way people discover
that next great read. Help us steer the ship.
Send us feedback.
(Also, there's always a feedback link in the top right corner of the web page.)
