Abstract:Recommendation systems for the mobile Web have focused on endorsing particular types of content to users. Today, mobile service providers have a more direct recommendation channel, namely the short messaging service. Therefore, mobile service providers should consider both the timing and context of recommendation messages (push messages) that are sent to users. Mobile service providers can learn context‐specific user preferences by analysing mobile Web use logs and user responses to push messages. In this paper, we present a context‐sensitive recommendation system that can be used to select the optimal context in which to send recommendation messages. We call this system the mobile context recommender system (MCORE). We compared user responses to push messages delivered in and out of suitable contexts as determined by MCORE. The precision of push messages delivered within a suitable context was higher than that of messages delivered outside of one.

In the face of increasing global competition and complexity of the socioeconomic environment, many organizations employ groups in decision making. Inexact or vague preferences have been discussed in the decision-making literature with a view to relaxing the burden of preference specifications imposed on the decision makers and thus taking into account the vagueness of human judgment. In this article, we present a multiperson decision-making method using fuzzy logic with a linguistic quantifier when each group member specifies incomplete judgment possibly both in terms of the evaluation of the performance of different alternatives with respect to multiple criteria and on the criteria themselves. Allowing for incomplete judgment in the model, however, makes a clear selection of the best alternative by the group more difficult. So, further interactions with the decision makers may proceed to the extent to compensate for the initial comfort of preference specifications. These interactions, however, may not guarantee the selection of the best alternative to implement. To circumvent this deadlock situation, we present a procedure for obtaining a satisfactory solution by the use of a linguistic-quantifier-guided aggregation that implies the fuzzy majority. This is an approach that combines a prescriptive decision method via mathematical programming and a well-established approximate solution method to aggregate multiple objects. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 641–660, 2007.

Abstract: Customer retention is a critical issue for the survival of any business in today's competitive marketplace. In this paper, we propose a dynamic procedure utilizing self-organizing maps and a Markov process for detecting and preventing customer defection that uses data of past and current customer behavior. The basic concept originates from empirical observations that identified that a customer has a tendency to change behavior (i.e. trim-out usage volumes) before eventual withdrawal and defection. Our explanatory model predicts when potential defectors are likely to withdraw. Two strategies are suggested to respond to the question of where to lead potential defectors for the next stage, based on anticipating when the potential defector will leave. Our model predicts potential defectors with little deterioration of prediction accuracy compared with that of the multilayer perceptron neural network and decision trees. Moreover, it performs reasonably well in a controlled experiment using an online game.