2012 | OriginalPaper | Buchkapitel
An Intelligent Recommendation System for Individual and Group of Mobile Marketplace Users Based on the Influence of Items’ Features among User Profile
verfasst von : Amer A. Sallam, Siba K. Udgata, Vineet Padmanabhan
Erschienen in: Global Trends in Computing and Communication Systems
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
With the expansion of the wireless services, the number of mobile users has rapidly increased and the quantity of information on the internet and in wireless medium has also increased exponentially. This much information becomes difficult to be monitored by users well as searching for specific data may cost a lot in terms of time. Moreover, in the mobile scenario, only simple search and browsing functions are available due to limited computing power of a mobile phone. Therefore, it is more preferable to let the desirable information find the customers rather than to let them search for specific information when it is needed. This can be realized by integrating personalized user preferences along with justification recommendation system such that necessary information find the mobile user and alleviate the burden of search for that information when it is needed. This paper proposes an effective recommender system that can help consumers formulate better purchasing decision by incorporating support for user features. This system is not only recommends items to user based on their interest, but also attempt to recommend the nearest location place of the item. The proposed framework has the potentiality to increase consumer satisfaction, enhance consumer/company loyalty, and boost overall sales by giving justification and creditability to the products that have high degree of interest to consumers. The results show a significant promise in the system’s ability to make accurate recommendations to the users.