Development of accommodation facility selection recommendation system

A collaborative filtering recommends a list of items to a given user, to which he is expected to prefer to, considering a history of purchase items of the user and those of other users, and it is applied to many web shopping sites. On the other hand, although many people often reserve accommodation facilities from web pages, it is difficult to apply the collaborative filtering to accommodation selection because a smaller sizes of an item (an accommodation) history than others reduces the number of user and item to which the collaborative filtering can be applied. To solve it, we introduce a virtual user, who is assumed to rank all of accommodation facilities, to the collaborative filtering, which can increase the number of recommendable user-item pairs. We design the virtual user by analyzing an actual data set of accommodation. Numerical experiments show the virtual user can increase the number of change on user-item pairs which is recommendable without the virtual user.