Findka
AI
recommender system
SHOW HN2020
How HN took it
4 positive, 13 neutral or asking, 1 mixed, 3 critical, out of 21 comments about the project. Thread score -0.02.
Idea: 1 for, 1 againstDesign: 1 for, 1 againstExecution: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Gnod and Gnoosic-style discovery is useful
From 1 comment
Reminds me of Gnod, the Global Network Of Discovery: https://www.gnod.com For music, Gnod definitely gives me better suggestions then iTunes and Youtube.
TicklishTiger on HN
Objections
Cross-domain correlation between content types may be weak
From 2 comments
It's an interesting idea. Do you have reason to believe that people's preferences in different areas are correlated? Not saying they're definitely not, but that's my first…
aabeshou on HNI am going to share a piece of anedoct. There once was a very nice German-based application called Foundd. The app was soecialised in movie recommendation and it was awesome:…
brmgb on HN
Cold start: new users get irrelevant items they cannot rate
From 2 comments
I love the sound of this. But wouldn't it be productive for users to initially "seed" a category (say, Movies) by entering a handful of films they liked and ones they didn't…
steveharman on HNBiggest advise I can give is that you should do a better job at content seeding to ensure that first time users have a good experience. Otherwise, you'll never get better from…
victor9000 on HN
Music recommendations feel mainstream and poor
From 1 comment
> I started working on recommender systems in 2016 during my undergrad, specifically doing music recommendation (I was dissatisfied with the quality of Pandora/Spotify…
xerox13ster on HN
Requests
Seed preferences with a search box for items
From 2 comments
I love the sound of this. But wouldn't it be productive for users to initially "seed" a category (say, Movies) by entering a handful of films they liked and ones they didn't…
steveharman on HNNeat idea, this could become a valuable resource for discovering interesting things. From a UI perspective: Maybe there could be a searchbox for books, songs etc. so that one can…
julvo on HN
Import ratings from Letterboxd, Goodreads and similar services
From 1 comment
This would be much better if it allowed you to import ratings from other popular rating services (letterboxd, goodreads, RYM, etc.)
bobcostas55 on HN
Option to change number of recommendations in newsletter
From 1 comment
Very interesting. Learned about Findka in your music recommendation service newsletter. - I'd like to change how many recommendations I get with each newsletter. - I'd like to…
emaro on HN
Questions
How correlated are preferences across content types?
From 1 comment
It's an interesting idea. Do you have reason to believe that people's preferences in different areas are correlated? Not saying they're definitely not, but that's my first…
aabeshou on HN
How well does it scale in users and data?
From 1 comment
You mention storing the matrix in memory and recomputing hourly because of the small data set. What are your estimates for scaling ceiling with current implementation? How many…
Thespian2 on HN
Alternatives named
Gnod
From 1 comment
Reminds me of Gnod, the Global Network Of Discovery: https://www.gnod.com For music, Gnod definitely gives me better suggestions then iTunes and Youtube.
TicklishTiger on HN
Gnoosic
From 1 comment
Definitely. Gnoosic in particular was an inspiration for the current iteration of Findka (https://www.gnoosic.com/).
jacobobryant on HN
Stumbleupon
From 1 comment
This reminds me of Stumbleupon[1] from back in 2005-ish. I used to love using it before they decided to pivot and remove all of the things that made it great. [1]…
devnonymous on HN
Foundd
From 1 comment
I am going to share a piece of anedoct. There once was a very nice German-based application called Foundd. The app was soecialised in movie recommendation and it was awesome:…
brmgb on HN
Spotify Discover Weekly
From 1 comment
I've wondered about this a lot. It seems to be hit or miss--some people love e.g. Spotify's discover weekly/daily mix playlists, and some people hate them. I suspect that some…
jacobobryant on HN