A beer recommendation system made with R

June 24, 2013
By

(This article was first published on Revolutions, and kindly contributed to R-bloggers)

If you know a beer you like and want some recommendations for a style of beer to try, check out the yhat Beer Recommender:

Beer recommender
This neat little app is the product of a recommendation system built using the R language by the folks behind the yhat blog. It's based on about 1.5 million beer reviews from the Beer Advocate. The ratings were read into a Postgres database and then imported to R using the RPostgreSQL package. From there, you can easily make a start at collaborative filtering in R by using the intersect function to identify all reviewers that have rated a particular pair of beers, and write a distance function in R to measure how close the two beers are according to the reviewers' ratings. Do this for all pairs of beers (using a neat application of the expand.grid function), put the results behind a JavaScript UI, and you've got yourself a beer recommender. (This is similar to the approach used for this recommendation engine for movies.) Check out the full details including R code at the link below.

yhat blog: Recommendation System in R

To leave a comment for the author, please follow the link and comment on his blog: Revolutions.

R-bloggers.com offers daily e-mail updates about R news and tutorials on topics such as: visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...



If you got this far, why not subscribe for updates from the site? Choose your flavor: e-mail, twitter, RSS, or facebook...

Comments are closed.