Sign in with Facebook
Recommendations And Discovering Good Reads
Many of you have given us feedback that you'd like to see book recommendations on Goodreads from a Netflix-style algorithm. We've always agreed, but good recommendation algorithms are really (really!) difficult to do right. We built Goodreads so that you could find new books based on what your friends are reading, and now we want to take the next step to make that process even more fruitful.
To tackle this highly complex challenge, Goodreads has acquired a company by the name of Discovereads.com. With their deep algorithmic book recommendation technology, we’re going to be able plumb our database of 100 million book ratings from 4.6 million users to find general patterns of the kinds of books people read and to generate high-quality personalized recommendations.
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 and self-published books has made the market even larger. It’s a really, really, hard problem to get right, and we we’re excited to have the Discovereads team onboard, because along with being great people, they have a background in machine learning algorithms.
Inspired by the Netflix prize (and with some direct help from a member of second place team), Discovereads’ Brian Percival, left his PhD at Stanford University in Electrical Engineering (in neural circuitry software modeling) to pursue this project. Together with CEO Kyusik Chung, the company has taken three years to refine the technology.
Discovereads combines multiple machine learning algorithms and graph analysis techniques to analyze book ratings and spot trends. Its technology will also improve our unique targeted advertising program. Currently, authors and publishers can purchase ads for their books and target the ads to members who have read similar genres. Hopefully, the new technology will make it more likely that when you see a sponsored book, it will be even more likely it’s something that you’re interested in!
We expect to have Discovereads fully integrated within the next few months. And as always, when it goes live, we will welcome your feedback!
To tackle this highly complex challenge, Goodreads has acquired a company by the name of Discovereads.com. With their deep algorithmic book recommendation technology, we’re going to be able plumb our database of 100 million book ratings from 4.6 million users to find general patterns of the kinds of books people read and to generate high-quality personalized recommendations.
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 and self-published books has made the market even larger. It’s a really, really, hard problem to get right, and we we’re excited to have the Discovereads team onboard, because along with being great people, they have a background in machine learning algorithms.
Inspired by the Netflix prize (and with some direct help from a member of second place team), Discovereads’ Brian Percival, left his PhD at Stanford University in Electrical Engineering (in neural circuitry software modeling) to pursue this project. Together with CEO Kyusik Chung, the company has taken three years to refine the technology.
Discovereads combines multiple machine learning algorithms and graph analysis techniques to analyze book ratings and spot trends. Its technology will also improve our unique targeted advertising program. Currently, authors and publishers can purchase ads for their books and target the ads to members who have read similar genres. Hopefully, the new technology will make it more likely that when you see a sponsored book, it will be even more likely it’s something that you’re interested in!
We expect to have Discovereads fully integrated within the next few months. And as always, when it goes live, we will welcome your feedback!
Comments Showing 1-50 of 84 (84 new)
Yup - Discovereads signups are already disabled, and we will be shutting it down and moving the recommendation software over to Goodreads as fast as we can!
I have good luck with Netflix too and am looking forward to this new feature. My bookshelves are already screaming for mercy as it is, I fear they may completely collapse after this feature is implemented.
I think that this is wonderful for quickly seeing what is available that we may not have heard about... there are a lot of books out there that deserve attention but haven't got the buck for the press bang. I am curious however if it would be possible to add in a feature to the compare bookshelf feature between users to show those users that have the highest rate of compatibility to you instead of having to wade through random users?
It will be great to have recommendations on GoodReads, but I do hope they'll be good ones. I've tested Discovereads a bit, and have yet to receive any quality recommendations. :( It also didn't know about a lot of the books I've read (but which are listed on GoodReads).
Should be an interesting implementation!
I can't wait for the site to start accepting more members!
Oh my goodness!! I'm so excited about this! My brother was just telling me yesterday that goodreads needs something like netflix recommendations. I can't wait to flash this post in front of his face! :)
I think this will be great - although one of the drawbacks of the Netflix system is that I can't fill out or create my own "rules". We don't watch R rated movies. But I get MANY recommendations for rated-Rs that are similar to those I like, but I just can't bother with the system that can't see that - and gives me 1000s of recommendations for things I *won't* watch, even if I might enjoy it. ps and yes I realize that books don't have content ratings etc. But just pointing out a flaw in other recommendation systems.
This will be terrific....I hope to not only use it for myself but to expose my students to this feature. I think they will really put it through it's paces.Thanks for this terrific improvement.
What I want to know is why half the things on here don't work for me and why I can no longer get the book giveaways to work now? What;s going on?Debby Creager
Congratulations. Looking forward to seeing what they bring to the table.
Great, I really don't care what my "social media friends", I care about good books. It's good to hear that you concentrate more on being a book database with recommendations and less on all that boring social media stuff.
I still think we're missing the mark here people! Isn't this suppose to be a community?I'm new here so maybe I'm wrong but I don't want recommendations based on what a computer thinks I'll like. I want to see recommendations to people that share my reading interests. Have you ever walked into someones house and seen their book self and got excited when they like some of the same books you do? That's how the conversation gets started to where you get introduced to new lit you never thought of trying. "hey man, if you liked this book then you should try this one. it starts a little slow but if you can make it threw the 2nd chapter it really takes off" Not book recommendations, book shelf and people recommendations! lets make new friends!
Just registered one day ago and was going to contact you for something like this. Great job guys!
Looking forward to it! Will recommendations be delivered via the regular Goodreads email, or on the site itself? Both?
Yahoo! Can't wait to use it. Another wonderful reason to use GoodReads.
it sounds amazing. I sure am excited about it.
Wow, this sounds awesome!I don't know if you are up for suggestions and if any editing can really be done....
But I love reading a variety of genres. Will there be a way to find recommendations based on genre? Or can we find books similar to a recently reviewed book?
I'm just worried that my variety of genres is going to skew the results.
Very good! A must feature!Im waiting for how this turns up!
Hope its better than Amazon recommendations :)
Jason wrote: "I still think we're missing the mark here people! Isn't this suppose to be a community?I'm new here so maybe I'm wrong but I don't want recommendations based on what a computer thinks I'll like. I ..."I am sure you CAN still talk to people and get human recommendations!
It is just a very neat extra feature... No one forbids you to make friends...
Valerie wrote: "It will be great to have recommendations on GoodReads, but I do hope they'll be good ones. I've tested Discovereads a bit, and have yet to receive any quality recommendations. :( It also didn't k..."I think that was the problem with discoverreads is that the have a small database.
For a thing like that to work you have to have a really good algorithm and a very large database.
Goodreads being the most popular site of this kind has most likely the largest database possible, so with their database and with Discoverreads algorithm this could work wonders.
I just hope their algorithm won't proritise popular books and let us discover hidden gems!
This is great news! Relatedly, I manually ported all of my goodreads reviews to Amazon a few months ago in order to take advantage of their recommendations.Somewhat surprisingly, I've found the experience to be absolutely TERRIBLE. I will typically have to scroll through multiple pages of recommendations before I find one I'm interested in trying out.
Amazon's recommendation system seems to rely extremely heavily on books by authors you've already purchased. So, if I loved a The Sun Also Rises or Ender's Game, for example, my suggestions list will immediately become littered by every Hemingway or Orson Scott Card book ever written. Nor does Amazon seem to take the hint if I manually check "I'm not interested" for each one.
So, I know that recommendations are a very tricky art, but I do hope that Goodreads takes a more "netflixy" approach than an "amazony" one. I want to be exposed to quality books and authors that I don't already know, not be shown the lesser works of the authors I already do know.
Just the direction I'm happy to see Goodreads go in. I love getting recommendations from friends, but that depends on someone I know reading another book. How many good books go unrecognized that way. Can't wait to see this in action! If there were only more hours in the day to read!?!
Great! This'll be really handy. Thanks for putting so much work into Goodreads! I'm really glad I joined.
Can't wait to see my bookish recommendations!
Danielle wrote: "I think that this is wonderful for quickly seeing what is available that we may not have heard about... there are a lot of books out there that deserve attention but haven't got the buck for the pr..."I think that it would be awesome to be able to find our most compatable users. And the recommendation software sounds very interesting. I am excited :)
I just discovered the link that compares popular books amoung my friends. I think that is fantastic and very helpful.
Great news greats steps forward for the love of reading.
Yaaaay. That's great! I always need some good book recommendations.
I also don't care what my social media friends are reading - at least not for picking books for myself. I hope there will be a way to get recommendations based on what I've read and liked before. That would be PERFECT!
Jason wrote: "I still think we're missing the mark here people! Isn't this suppose to be a community?I'm new here so maybe I'm wrong but I don't want recommendations based on what a computer thinks I'll like. I ..."What you want already exists. Take on some "friends" or "follow" people who look interesting to you and you get to see their reviews and the books they have put on there "to read" shelves.
What the computers do is look at what you have rated and what you like. It is a "if you liked book X, you should look into book Y" which is what good book store people used to be able to do for us in the old days. (Not that I personally ever came across one of those good book store people!)
Michele wrote: "I also don't care what my social media friends are reading - at least not for picking books for myself. I hope there will be a way to get recommendations based on what I've read and liked before. T..."But your "social media people" here at Goodreads will be people who read the same kinds of books you enjoy. You will like the books they read and they will like yours.
Michael wrote: "This is great news! Relatedly, I manually ported all of my goodreads reviews to Amazon a few months ago in order to take advantage of their recommendations.Somewhat surprisingly, I've found the ..."
At Amazon you can tweak the recommendations for each book they suggest. You can tell them Not Interested, and they will make future recommendations based on those not interested ticks. You can tell them not to use certain books to make recommendations. (Generally very useful if you bought someone else a gift.)
Here is hoping they do something like that here too.
Let's see! Books and those who share, "let us discover hidden gems".
Hope this helps me. I like to read novels set in another country where I can both care about character and learn something new about culture or geography. Have been going to groups that have country as an interest, but is cumbersome to go to one country after another. Would like one group with a mixture. Does anyone know of such a group already in existence? The concern I have about book recommendations based on my list of nearly 800 books is that many of those were read years ago and I no longer have same interests.
with these step we can say now we have a Global civilization
I'm really looking forward to this!