Making smartphone service recommendations by predicting users' intentions: A context-aware approach

The current popularity of smartphones has resulted in the rapid development of many smartphone application programs that offer various mobile and other pervasive services. To provide smartphone users with timely access to the most useful and desired services, this study develops a recommendation mechanism to predict user intention and activate the appropriate services. We choose to employ the event-condition-action model together with a rule induction algorithm to discover smartphone users' behavior patterns, which are then exploited to predict and recommend services that the user may desire. We employ a fuzzy clustering method to reduce rule complexity. A series of experiments are conducted to validate the developed system, and the results are analyzed in detail to investigate the success of the various strategies. The results demonstrate that our approach has substantial promise.