Goodreads has tapped its six million members to create a new book recommendation engine, analyzing reader opinions about 190 million books stored on their digital shelves.

CEO Otis Chandler explained in the release: “No one has been able to provide recommendations like this before.  This is the first time a community of readers of this size has collectively shared their literary likes and dislikes … It gives us data that no one else has.  For example, we have more than 174,000 ratings of the best-selling ‘The Help’ while Amazon only has around 4,400.”

To test the recommendations, simply visit this link–you must rate at least 20 books to get an accurate reading of your literary tastes. The new feature relies on a collection of secret algorithms to predict what kind of books a new reader will enjoy.