Personalized Service Recommendation Based on User Dynamic Preferences

Abstract

In order to personalize users’ recommendations, it is essential to consider their personalized preferences on non-functional attributes during service recommendation. However, to increase recommendation accuracy, it is essential that recommendation systems include users’ evolving preferences. It is not sufficient to only consider users’ preferences at a point in time. Existing time-based recommendation systems either disregard rich and useful historical user invocation information, or rely on information from similar users, and thus, fail to thoroughly capture users’ dynamic preferences for personalized recommendation. This work proposes a method to personalize users’ recommendations based on their dynamic preferences on non-functional attributes. First, we compose a user’s preference profile as a time series of his/her invocation preference and pre-invocation dependencies (i.e. the different services that were viewed prior to invoking the preferred service). We model a user’s invocation preference as a combination of non-functional attribute values observed during service invocation, and topic distribution from WSDL of the invoked service using Hierarchical Dirichlet Process (HDP). Next, we employ long short-term memory recurrent neural networks (LSTM-RNN) to predict the user’s future invocation preference. Finally, based on the predicted future invocation preference, we recommend service(s) to that user. To evaluate our proposed method, we perform experiments using real-world service dataset, WS-Dream.