Learning Relational User Profiles and Recommending Items as Their Preferences Change

Abstract

Over the last decade a vast number of businesses have developed online e-shops in the web. These online stores are supported by sophisticated systems that manage the products and record the activity of customers. There exist many research works that strive to answer the question "what items are the customers going to like" given their historical profiles. However, most of these works do not take into account the time dimension and cannot respond efficiently when data are huge. In this paper, we study the problem of recommendations in the context of multi-relational stream mining. Our algorithm "xStreams" first separates customers based on their historical data into clusters. It then employs collaborative filtering (CF) to recommend new items to the customers based on their group similarity. To evaluate the working of xStreams, we use a multi-relational data generator for streams. We evaluate xStreams on real and synthetic datasets.

Web service recommendation based on time‐aware users clustering and multi‐valued QoS prediction

“…The shifting of service bias is the most used time effect in this category of TARS. Moreover, most continuous time‐aware approaches adopt either collaborative filtering or hybrid filtering …”

Time‐aware service recommendation: Taxonomy, review, and challenges

“…Shifting of service bias is the most used time effect in this category of TARS. Moreover, most continuous time‐aware approaches adopt either collaborative filtering or hybrid filtering …”

“…The hybrid filtering was less used. It was presented only in three approaches . This could be explained by the long time spent, when combining two or more filtering techniques.…”

“…The window time is an important factor while recommending services since it indicates after how much time we should update the ratings (eg, per day, per week, per month). However, it was ignored in most of the approaches, except in few ones like in other works …”

“…This is due to the rapid change in service information compared to the change of users preferences and information and the need to consider it for better recommendations. The shifting of user preferences was less used because of the difficulties faced in order to extract the users' needs …”