Regression Model for Context Awareness in Mobile Commerce

This work presents a novel approach, socalled RBCM, in modeling a domain to construct contextaware model for mobile computing. RBCM is based on a multivariate regression method to construct a probability density function for action schema in a domain. A machine learning algorithm is applied to map the action schema with a context. RBCM is evaluated using a benchmark dataset. The results are compared with the start-of-the-art rivals of RBCM. The main candidate rivals of RBCM are based on the latest variations of Nayes-bias, MOCART and Decision Tree. The results show that our model outperform its rival techniques in accuracy and precision. RBCM predicts the preferences of the users with a higher accuracy than its rivals. RBCM perform better with the sample size greater than 50.