NotifyMiner: rule based user behavioral machine learning approach for context wise personalized notification services

This paper devises the issue of machine learning rule-based methodology for uncovering the behavior-based rules of respective smart-phone users for purpose of providing context wise individualized notification services. Nowadays, the number of notifications arrived at an inappropriate moment of time or carried unrelated material, which can cause disruption. Previously Rule-based Classifier and Association Rule Mining (ARM) Techniques have been used to solve those problems. However, the classifier approach processes accuracy and reliability problems because of small data instances. ARM creates a vast number of redundant rules, which are pointless for creating context-aware decisions. Redundant rules can make the approach non-efficient and also make the dataset unnecessarily large, making decision-based problems more complicated. For those problems solution in this article, we propose a new Behavioral Adversarial Traversal Tree approach for extracting user behavioral rules with respect to different contexts. A real-world dataset is collected to make this approach more relevant. The Proposed approach effectively identifies and removes the redundant rules with individual behavior-oriented time slots, which are used in the proposed approach to make it more exact and efficient. Our experiments and comparisons on each individual contextual dataset exhibit that the following rule discovery approach is more adequate and more exact for context-aware notification services.