We just launched a new feature that lets you enter a book/author you love and see which books readers who also loved that book/author liked as part of our "3 favorite reads" of the year poll.
We are also building a full Book DNA app, which pulls in your Goodreads history and delivers deeply personalized book recommendations based on people who like similar books.
It’s an interesting challenge. Modern recommendation systems grew powerful because of enormous amounts of instant feedback. You can capture clicks and view time on the web. You don’t get that in books.
I see three possible solutions:
1. Google approach: scrape the web for book recommendations and somehow create an ML recommendation system that’s better than Goodread’s
2. Pandora Radio approach: (semi-)manually create classifiers for books (genre, tone, character traits, etc.) and build a recommendation system with that.
3. Practical approach: find book reviewers whose opinions you trust and follow their recommendations.
Do you mean one should post their reviews of last 10 books read into Gemini and then ask it to find 20 rare-gems books based on the content of those reviews?
One of the services that I know is Shepherd https://shepherd.com. The service is like Goodreads, but it's more personalized. Shepherd is trying to help the readers to discover and share the books. I am not the author. You can read the details on https://build.shepherd.com/p/what-is-shepherds-mission-for-r....
Last but not least, this is the example of someone's favorite books https://shepherd.com/bboy/2024/f/william-hansen.
Thank you for the kind words, super motivating :)
We just launched a new feature that lets you enter a book/author you love and see which books readers who also loved that book/author liked as part of our "3 favorite reads" of the year poll.
Try it out here: https://shepherd.com/bboy/2025
What do you think?
We are also building a full Book DNA app, which pulls in your Goodreads history and delivers deeply personalized book recommendations based on people who like similar books.
You can sign up to beta test it here if you want to help me on that: https://docs.google.com/forms/u/1/d/1VOm8XOMU0ygMSTSKi9F0nEx...
The first beta is coming out in late January, but it's pretty basic to start. Very early preview here as we build it: https://www.youtube.com/watch?v=BUMJ6uLNfjM&feature=youtu.be
You might try this: https://shepherd.com/my-book-dna
This is an early beta as we work on this problem; I want deeply personalized book recommendations for similar readers.
What do you think of the results?
It’s an interesting challenge. Modern recommendation systems grew powerful because of enormous amounts of instant feedback. You can capture clicks and view time on the web. You don’t get that in books.
I see three possible solutions:
1. Google approach: scrape the web for book recommendations and somehow create an ML recommendation system that’s better than Goodread’s 2. Pandora Radio approach: (semi-)manually create classifiers for books (genre, tone, character traits, etc.) and build a recommendation system with that. 3. Practical approach: find book reviewers whose opinions you trust and follow their recommendations.
I thought https://book.sv was pretty good. It was on HN recently: https://news.ycombinator.com/item?id=45825733. When I inputted 5 books I liked, the recommendations were a combination of:
1. books I had already read and enjoyed before
2. books that were already on my list (either from friends or other recommendations)
3. books I hadn't heard of
That said, I haven't read a book from #3 yet, so I can't fully vouch for it, but #1 and #2 are positive signals to me.
Once you cross 100 books its all repetition. Just like HN comments.
Paste in last 10 reviews to Gemini or gpt and ask for 20 "rare-gems, unique and exquisite," with descriptions. Works well
Sorry, I couldn't understand your comment fully.
Do you mean one should post their reviews of last 10 books read into Gemini and then ask it to find 20 rare-gems books based on the content of those reviews?