3. Author xlvector, Copyrights belong to CASIA
Abstract
Recommender System is an important tool for users to discovery information
of their interest, it is also an important tool to overcome information overload
problem. The main idea of recommender system is to make recommendation by
analyzing users’ historical behaviors. Early researches on recommender system
always neglect temporal information, and most of them are focused on the anal-
ysis of users’ static behaviors. In recent years, because of Netflix Prize, more and
more data sets including temporal information are released, and more and more
researchers are studying on temporal recommendation problem. However, there
are many problems left in this research area.
This paper investigate the temporal recommendation problem by analyzing
many public released data sets. Following are main contributions of this paper:
1 Temporal recommendation for rating prediction problem: Rating predic-
tion problem is the most famous problem in recommender system, its main
task is to predict a given user’s rating on a given item by analyzing her his-
torical rating on other items. In this paper, we incorporate temporal infor-
mation into this problem, and propose a latent factor model to model four
different temporal effects. Furthermore, we also proposed a cascade model
to model seasonal effects. Experimental results show that our method can
achieve higher accuracy in rating prediction problem than non-temporal
methods.
2 Temporal recommendation for top-N recommendation problem: Top-N rec-
ommendation problem is the most important problem in real recommender
system, its main task is to recommend N items to every user which will be
of their interests by analyzing users’ historical behaviors. In this paper, we
introduce a new type of node, session node, into user-item bipartite graph
to model users’ long term and short term interests. Furthermore, we also
proposed a new graph-based personal ranking method called PathFusion to
4. Author xlvector, Copyrights belong to CASIA
iv 动态推荐系统关键技术研究
make recommendation by the new graph model. Experimental results show
that our method can make higher accuracy than non-temporal methods and
other temporal recommendation methods in top-N recommendation prob-
lem.
3 Influence of system update rate on recommender system: User behavior is
influenced by social factor and personal factor. However, in the websites
with different update rates, these two factors will have different influence.
In fast updating sites, users are more influenced by social factor while in
slow updating sites, users are more influenced by personal factor. In this
way, we need different recommender systems in web sites with different
update rates. We proposed a session graph model which introduce two new
types of nodes into user-item bipartite graph to model social factor and
personal factor. By controlling the weight of these two new types of nodes,
the recommendation algorithm can control the influence of social factor
and personal factor on final recommendation results. Experimental results
show that our method can achieve high accuracy in systems with different
update rate.
4 Prototype of temporal recommender system: We design a prototype of
temporal recommender system. This system can return real-time recom-
mendation to users after they have new behavior, and can tune the ranking
of results by user feedback. In this way, this system can improve user
experience in real time by their feedback.
Keywords: recommender systems, personalization, collaborative fltering, tem-
poral effects, seasonal effects, temporal dynamics in recommender systems