Live data from Hacker News

I Want to Fix Goodreads

prepend.com

1–10 of 205 posts

Re: I Want to Fix Goodreads

#2
How do people build recommendation engines?

Like, even when you have access to the site's entire API and can write your own client for it, there's still the fact that their recommendations are generally better.

It sounds like an extremely important value-add. There are many sites that I will only use the app for because that is where the recommendations are shown. But to me taking a user profile and an article and spitting out a list of articles seems like magic.

I also find it weird that in 2020 Goodreads is the status quo for book recommendations.

Re: I Want to Fix Goodreads

#3

How do people build recommendation engines? Like, even when you have access to the site's entire API and can write your own client for it, there's still the fact that their recommendations are generally better. It sounds like an extremely important value-add. There are many sites that I will only use the app for because that is where the recommendations are shown. But to me taking a user profile and an article and sp…

The best recommendation engine is other people that you know and understand.

Re: I Want to Fix Goodreads

#4

How do people build recommendation engines? Like, even when you have access to the site's entire API and can write your own client for it, there's still the fact that their recommendations are generally better. It sounds like an extremely important value-add. There are many sites that I will only use the app for because that is where the recommendations are shown. But to me taking a user profile and an article and sp…

> How do people build recommendation engines?

Poorly, its either shovel so much shit against a wall to see what sticks (youtube) or you sorta watched this for 10 minutes to see if you liked it but you didn't but here is more (netflix).

Curated lists made by humans are still nicer.

Re: I Want to Fix Goodreads

#5

How do people build recommendation engines? Like, even when you have access to the site's entire API and can write your own client for it, there's still the fact that their recommendations are generally better. It sounds like an extremely important value-add. There are many sites that I will only use the app for because that is where the recommendations are shown. But to me taking a user profile and an article and sp…

It's not that hard. See for instance https://www.coursera.org/lecture/machine-learning/collaborat... on how to get started

Re: I Want to Fix Goodreads

#6

How do people build recommendation engines? Like, even when you have access to the site's entire API and can write your own client for it, there's still the fact that their recommendations are generally better. It sounds like an extremely important value-add. There are many sites that I will only use the app for because that is where the recommendations are shown. But to me taking a user profile and an article and sp…

For me, I only use goodreads because there’s nothing better that I’ve found. I think of it as similar to evolution, evolution is just about survival, not necessarily the best at stuff that’s not survival.

Re: I Want to Fix Goodreads

#7
post #5

How do people build recommendation engines? Like, even when you have access to the site's entire API and can write your own client for it, there's still the fact that their recommendations are generally better. It sounds like an extremely important value-add. There are many sites that I will only use the app for because that is where the recommendations are shown. But to me taking a user profile and an article and sp…

It's not that hard. See for instance https://www.coursera.org/lecture/machine-learning/collaborat... on how to get started

It's not hard to build something that gives you recommendations. It extremely difficult to build something that works well. For consumer companies I know only Spotify and TikTok that do it well, and Youtube that does it OK-ish.

Re: I Want to Fix Goodreads

#10
My problem with Goodreads isn't the recommendations engine. The recommendations are fine. I'm actually skeptical that any ML recommendation engine is going to recommend better books than my friends will. The only thing I expect from a recommendation engine is discovery, by which I mean finding new things that neither I nor my friends have read that look interesting. Whether they're good is another story altogether...

My problem with Goodreads is actually the site performance. It's one of the most abysmally slow sites I've ever had the displeasure of using. Loading from page to page takes so long, I wonder if they're running on 486 machines in the background. It's unfathomable to me how something that has such a monopoly on the domain can have such terrible performance.

It's so bad, that I often don't even bother going to Goodreads except when my TBR pile empties out, and then I spend as little time as I can (which is a long time because it's OH MY GOD SO SLOW) so I won't have to visit it again for a while.

I wish it was open source, or something, so I could contribute to improve response times...

Post reply on HN