How does Readgeek work?

It't pretty simple. You rate some books - about 10. To get the best prediction results also rate books you didn't like. For your recommendations we use two different approaches - one user based algorithm and one book based. For the user based method method we look in our database to find people with a book taste very close to yours. Their ratings of books unknown to you gives us an idea how you would like those books.
In the second method we look only at each book you rated and see which books is very similar. So if two books were rated by one group of users very high and by another group very low than this would give us a hint that the comparing book is similar to yours and you would probably like it the same.
All that helps us to make your book suggestions and calculate your predictions. Also the more books you rate, the better the predictions.

If you want to know more about algorithms and collaborative filtering let us know.