Creating a Beer Recommendation Engine | Hacker News Reader

Creating a Beer Recommendation Engine

willnetsky.github.io

That's cool. It's similar to a project a friend and I did a few years ago to build a search engine for Beer Advocate.[1] We just used Lucene for indexing, though.

[1]: https://github.com/derekpeterson/search-beer-advocate

Mean to go through this one day - Can anyone who has recommend?:

https://www.coursera.org/learn/recommender-systems

there's so much data available in the form of reviews and flavor profiles, etc. I will follow this project, best of luck.

Also - what's your favorite american brewer&beer and favorite non-US?

For me, I like Stone Brewing/Stone IPA and imported fav is Weissbier Brewery Munich/Franziskaner

BTW as of now it looks like I just get a list of similar beers - would be nice to be able to set a profile and a list of favorites or pull from your existing ratings on beer rating sites with a public API

Yup it seems like currently recs are based on content filtering techniques, based on defined properties of each beer. I'd be interested in seeing this project utilize a collaborative filter to take into account user interactions/ratings associated with each beer and then predict beers that people would enjoy based on their preferences.

I used collaborative filtering for movie recommendation (http://web.onetel.com/~hibou/morse/MORSE-Paper.html), and it worked well for that, and I'd probably use it for music too. Movies and music have quite complex "structure", making it hard to compare even similar examples. Dr Strangelove's most similar movie is probably Fail-Safe, but the two are still very different in many ways, aren't really interchangeable, and I wouldn't be surprised if someone liked one but not the other.

For beer, although there are many different styles, similar beers could more easily be substituted for each other (e.g. Sierrra Nevada Pale Ale and Brewdog Punk IPA). So if you couldn't get the one you asked for, you'd be happy with the other.

I have no hard evidence, though, and might be wrong. I didn't get the chance to apply my MORSE algorithm to beer, and it wasn't as generally applicable as I'd have liked. (See http://web.onetel.com/~hibou/morse/DeadOnTime.html)

Reply on news.ycombinator.com