mahout-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Pat Ferrel <>
Subject Re: Solr+Mahout Recommender Demo Site
Date Mon, 07 Apr 2014 15:46:31 GMT
Exactly so. Recording different types of input was one reason to build a site that looked good
enough to feasibly get a little traffic.

For instance, one of the recommendation types is “Based on videos you recently viewed”
You see these on detail pages as well as the recommend page. These detail pages views are
put in log files but also recorded in realtime for queries. The recently viewed videos are
used as a query on the similarity/indicator matrix. This yields somewhat weak results IMO,
partly because of the mismatch in actions. You are trying to recommend from the “liked videos”
indicator matrix using “viewed detail page” actions. This is a case for the cross-recommender
but I don’t have enough detail views yet to calculate a cross-indicator matrix so I make
do with the one I have.

The analogy of a shopping cart recommender might be the watchlist on the site. A user’s
watchlist indicates an item-set that interests the user. Once enough of these are collected
Solr will quite easily allow for queries against everyone’s watchlists using the user’s
watchlist as the query. Not as strong as buying things together in a shopping cart but still
may be of value. When you go to your watchlist page (not really implmented yet) you’d see
other videos from similar watchlists. This type of query could be combined with the watchlist
as a query on the liked-video indicator matrix to give better results. 

Other actions are also possible to use like search terms. An indicator matrix of search terms
and videos clicked could be blended with fultext search to get personalized search results—again
given enough usage.

The site is equipped to gather all of this data if there is enough traffic.

On Apr 6, 2014, at 10:33 PM, Ted Dunning <> wrote:

On Mon, Apr 7, 2014 at 5:18 AM, Pat Ferrel <> wrote:

> Combining this kind of metadata with CF data has been important to the big
> guys but elusive to the rest of us. And a recommender that seamlessly
> integrates the different methods is rare. Solr + Mahout does it better than
> anything I’ve seen on the OSS or pay software market.

Combining with meta-data is a huge deal.

Frankly, having many kinds of indicators in the index so that you can mix
and match is big as well (maybe half as big).  This lets you tune the
weight of different kinds of input.

View raw message