Figure 1 - uploaded by A.F. Norcio
Content may be subject to copyright.
A Generic system architecture for personalized recommender system in e-commerce and m-commerce
Source publication
It is apparent that m-commerce and e-commerce have various similarities from operational and services perspectives. However, at the same time, m-commerce has its own a unique technology driven business opportunities with its own unique characteristics, functions, opportunities and challenges. One successful application in e-commerce is personalized...
Context in source publication
Context 1
... on our recommender system framework for e-commerce (Zenebe & Norcio, 2005) to m- commerce, generic system architecture for personalized recommender systems for e-commerce and m- commerce is presented in Figure 1. This framework provides the ground for thorough comparison between e-commerce and m-commerce recommender systems. ...
Citations
... One of the most successful applications in online shopping, according to [4], is 'personalized recommendation services'. Recommendations are aimed at supporting shoppers in their various decision making processes while carrying out shopping activities online. ...
... One of the most successful applications in online shopping is 'personalized recommendation services' [17]. Recommender systems (RS) are software tools and techniques for providing suggestions to a user of a system [10]. ...
Item recommendation is the process of recommending goods sold on online stores to visitors and existing customers of the store to aid their shopping transactions processes. Majority of the online stores in Nigeria have their shopping systems implemented similar to foreign online stores' templates. Adapting these foreign shopping system templates to meeting the needs of Nigerian consumers has been quite challenging. This is due to the unavailability and sparsity of ratings needed by the systems for the generation of these recommendations, thus Nigerian online stores focus on the provision of non-personalized recommendations. The peculiarities of Nigerian consumers call for the provision of personalized item recommendations using alternative information other than ratings information. A hybrid item recommender system that has been demographically enhanced is being proposed in this paper. The model was formulated using the search method, user profiling and association rule mining for the content-based item recommendations. The vector similarity and the adjusted cosine similarity methods were used for formulating the collaborative item recommendations. The demographic item recommendations were then formulated using the clustering and association rule methods. The performance of the system was evaluated using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The results of the performance evaluation carried out on the system showed that the system was able to reduce the Mean Absolute Error of the existing system by 61.24% and the Root Mean Square Error by 37.23% in content-based recommendations. In collaborative recommendations, evaluation results further showed that the new system was able to reduce the Mean Absolute Error of the existing system by 63.16% and the Root Mean Square Error by 39.30%.
... They combine user profiling and filtering techniques to provide more pro-active and personal information retrieval systems and have been gaining in popularity as a way of overcoming the ubiquitous information overload problem. Much of the research on ubiquitous recommendation systems are related to mobile phones and have been examined under the term m-commerce [49]. Examples include: a ubiquitous shopping system called MyGROCER [24], MovieLens Unplugged (MLU) [34], Mobile Sales Assistant [40], Buying-net [23], and APriori [38] product recommendation system. ...
There are increasingly many personalization services in ubiquitous computing environments that involve a group of users rather
than individuals. Ubiquitous commerce is one example of these environments. Ubiquitous commerce research is highly related
to recommender systems that have the ability to provide even the most tentative shoppers with compelling and timely item suggestions.
When the recommendations are made for a group of users, new challenges and issues arise to provide compelling item suggestions.
One of the challenges a group recommender system must cope with is the potentially conflicting preferences of multiple users
when selecting items for recommendation. In this paper, we focus on how individual user models can be aggregated to reach
a consensus on recommendations. We describe and evaluate nine different consensus strategies and analyze them to highlight
the benefits of group recommendation using live-user preference data. Moreover, we show that the performance is significantly
different among strategies.
KeywordsConsensus–Group recommendation–Ubiquitous personalization services
... Dans ce cadre, les applications sont nombreuses et variées, nous pouvons mentionner par exemple le tourisme (Wan, 2009) ou la recommandation dans le domaine de la restauration (Hosseini-Pozveh et al., 2009). Le m-commerce a cependant certaines différences avec le e-commerce, comme la mobilité, la capacité de calcul limitée, les capacités de transmission, la taille de l'écran, la durée de la batterie, etc. (Zenebe et al., 2005). Tout comme en e-commerce, en m-commerce le système de recommandation peut être implanté soit sur le serveur soit sur le client (mobile). ...
Les systèmes de recommandation, et notamment le filtrage collaboratif, sont traditionnellement utilisés dans les domaines du e-commerce et de la navigation web pour suggérer des ressources pertinentes aux utilisateurs au moment adéquat. Dans des approches dites "modèle", nous pouvons trouver les modèles à base d'usage et les règles d'association. Dans la littérature, ces modèles sont présentés comme des systèmes temps-réel. Ces dernières années, le domaine du m-commerce a émergé, dans lequel les recommandations sont diffusées sur un mobile au lieu de l'écran d'un ordinateur. Il faut donc adapter les techniques de recommandation aux nouvelles contraintes des terminaux mobiles. En particulier, puisque le respect de la vie privée est un objectif important, une façon de la préserver est de stocker les systèmes de recommandation sur le mobile. Cependant, bien que les systèmes de recommandation à base d'usage sont temps-réel, la génération des recommandations est complexe, et dans le cas où ils sont stockés sur le mobile, ils peuvent ne plus être temps-réel. Dans cet article, nous proposons un nouveau système de recommandation incrémental, à base d'usage, dans le but d'obtenir des recommandations instantanées dans le cadre du m-commerce
... Research on ubiquitous computing has come up with a number of recommendation systems reaching out in the real world. Many of the works are related to mobile phones and have been performed under the terms m-commerce [47] and mobile shopping assistance [24] [3]. In addition, there have been a number of mobile applications focusing on price comparison [6] [13] instead of product recommendations. ...
Customer reviews and recommendations for products are pro- vided by almost all e-business platforms, supporting con- sumers when shopping on the web. Mobile and ubiquitous computing provide extended means to sense input data for recommendations and to make recommendations available for consumers when shopping in traditional stores. This work contributes a comprehensive design space that outlines design options for product recommendation systems using mobile and ubiquitous technologies. A visual notation for the design space is proposed, based on which existing sys- tems are categorized. Blank spaces are identified and con- crete possible extensions are proposed by the example of an existing mobile product recommendation system. Finally, general options for future research on product recommenda- tion systems using UbiComp technologies are discussed.
... There are several ways on-line businesses can track and discover the changes in customer needs. One way is to implicitly collect customers " browsing behaviour when interacting with the website [23]. Web log files are commonly used sources of web visitors " activities that are used to update and maintain on-line customers " profiles. ...
Recent studies have indicated an increase in customer profiling techniques used by e-commerce businesses. E-commerce businesses are creating, maintaining and utilising customer profiles to assist in personalisation. Personalisation can help improve customers' satisfaction levels, purchasing behaviour, loyalty and subsequently improve sales. The continuously changing customer needs and preferences pose a challenge to e-commerce businesses on how to maintain and update individual customer profiles to reflect any changes in customers' needs and preferences. This research set out to investigate how a dynamic customer profile for on-line customers can be updated and maintained, taking into consideration individual web visitors' activities. The research designed and implemented a decision model that analysed on-line customers' activities during interaction sessions and determined whether to update customers' profiles or not. Evaluation results indicated that the model was able to analyse the on-line customers' activities from a log file and successfully updated the customers' profiles, based on the customer activities undertaken during the interaction session.
... Moreover, consumers face similar risks in using both modes and use similar criteria in deciding to use them (e.g., Swilley and Goldsmith, 2007). There are, however, important differences between the two (Ghinea and Angelides, 2004; Knowledge@Wharton, 2007a; Turban et al., 2004; Zenebe et al., 2005). ...
... Thus, " m-commerce should be recognised as a unique technology-driven business opportunity with its own unique characteristics, functions, opportunities and challenges " (Zenebe et al., 2005, p.3). But what consumer characteristics best predict which consumers will adopt? ...
The spread of handheld wireless devices gives firms new opportunities to transact business with customers through mobile technology, also referred to as mobile commerce. This paper describes a study of the antecedents of attitudes toward, and intentions to use, mobile commerce. We used data from 296 US student consumers to test our model. The results showed that experience with e-commerce positively influences consumers' perceived involvement with mobile commerce and their assessments of its perceived usefulness and perceived ease of use. These factors lead to positive attitudes toward, and positive intentions to use, mobile commerce.
