A Device-Similarity-Based Recommendation System in Mobile Terminals

Lei, Kai; Qian, Ying; Rui, Ning

doi:10.1109/icndc.2013.24

Cited by 1 publication

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To resolve the problems of the existing systems, Zheng et al ( 2010) grouped users who were similar and could be assisted with the same recommendation mechanism. Similar methodologies have been applied in studies including Lei et al (2013), who grouped users by device similarity, and Yin et al (2015) and have been shown to be an effective means for resolving the big data problem associated with group mobile recommendation. A user can also join the recommendation process by annotating his or her GPS trajectory based on which of his or her preferences can be learned (Zheng et al 2012).…”

Section: Introductionmentioning

confidence: 99%

Integer nonlinear programming and optimized weighted-average approach for mobile hotel recommendation by considering travelers’ unknown preferences

2016

View full text Add to dashboard Cite

The existing mobile hotel recommendation systems are usually subject to a difficult problem-travelers choose dominated hotels. This problem is difficult to resolve because there is no reason to recommend a hotel that is inferior to another in all aspects. To address this problem, an artificial dimension is added to each hotel to model unknown personal preferences. The possible values along the artificial dimension and the weight associated with it are derived by solving an integer nonlinear programming problem. Thus, the proposed methodology hybridizes objective and subjective weights. An illustrative example is provided to show the applicability of the proposed methodology. In addition, a field study was conducted in a small region of Seatwen District, Taichung City, Taiwan to evaluate the possible advantages of the proposed methodology over existing methods. The experimental results showed that the proposed methodology outperformed five existing methods in improving the successful recommendation rate, with the most significant advantage being up to 33 %. Furthermore, the recommendation results generated using the proposed methodology were found to be less risky.

show abstract

Section: Introductionmentioning

confidence: 99%