Digital commerce, with endless catalogs of items, can only thrive through recommendation engines,
suggesting likable items to a user based on the items she liked in the past, or based on items liked
by other users, with similar tastes. recommending appropriate ite
Many approaches, including collaborative filtering, have been developed to recommend items to users, based on the items they bought (and probably liked) previously, or based on the items that others users liked.
Collaborative filtering is one major approach behind recommenders, mapping items and users in the
same so-called latent space.
The PhD topic aims at leveraging collaborative filtering to tackle the social problem of
mismatch between job openings and job seekers.