A Hybrid Service Recommendation Prototype Adapted for the UCWW: A Smart-City Orientation

Abstract

With the development of ubiquitous computing, recommendation systems have become essential tools in assisting users in discovering services they would find interesting. This process is highly dynamic with an increasing number of services, distributed over networks, bringing the problems of cold start and sparsity for service recommendation to a new level. To alleviate these problems, this paper proposes a hybrid service recommendation prototype utilizing user and item side information, which naturally constitute a heterogeneous information network (HIN) for use in the emerging ubiquitous consumer wireless world (UCWW) wireless communication environment that offers a consumer-centric and network-independent service operation model and allows the accomplishment of a broad range of smart-city scenarios, aiming at providing consumers with the "best" service instances that match their dynamic, contextualized, and personalized requirements and expectations. A layered architecture for the proposed prototype is described. Two recommendation models defined at both global and personalized level are proposed, with model learning based on the Bayesian Personalized Ranking (BPR). A subset of the Yelp dataset is utilized to simulate UCWW data and evaluate the proposed models. Empirical studies show that the proposed recommendation models outperform several widely deployed recommendation approaches.

Emerging Perspectives on the Application of Recommender Systems in Smart Cities

“…Recommender system indicators are metrics or measures used to evaluate and measure the effectiveness and performance of a recommender system [38]. These indicators, are used to quantify the degree of accuracy, relevance, and usefulness of the recommendations provided by the system [39]:…”

FeatureMF: An Item Feature Enriched Matrix Factorization Model for Item Recommendation

“…For example, side information that may be extracted via social networks [9], [21], user demographics [11] or reviews from users [13], [14], has been successfully incorporated into CF and has been proven helpful at improving recommendation performance. In terms of approaches that exploit side information, works such as [18]- [20], [22], [23] propose the construction of a heterogeneous information network (HIN) based on user/item side information in order to learn relations between user/items. Other works, taking a different approach, i.e.…”