Investigating the use of association rules in improving recommender systems

Abstract

Recommender systems are widely used online
to help users find other products, items etc that they
may be interested in based on what is known about that
user in their profile.
Often however user profiles may be short on information
and thus when there is not sufficient knowledge
on a user it is difficult for a recommender system to
make quality recommendations. This problem is often
referred to as the cold-start problem.
Here we investigate whether association rules can
be used as a source of information to expand a user
profile and thus avoid this problem, leading to improved
recommendations to users. Our pilot study shows that
indeed it is possible to use association rules to improve
the performance of a recommender system. This we
believe can lead to further work in utilising appropriate
association rules to lessen the impact of the cold-start
problem.