Using Self-Histories to Predict Store Visits in Indoor Retail Environments for Mobile Advertising: A Ranked-Based Technique

Mobile advertising is expected to be the killer application in mobile business, and many researchers are exploiting different methods to generate a list of advertisements that could capture the interest of a targeted mobile phone user with high probability. In this paper, we present the Stores Visiting Patterns (SVP) algorithm to predict the set of stores that could be visited by a client in his/her next visit to the shopping centre. Here, a trajectory is a sequence of stores visited by a user, not necessarily the actual physical path/walk taken by the user when visiting the stores. Every trajectory pattern and visiting-pattern analysis is related exclusively to the profile of a registered client, i.e., We use self-histories rather than the histories of others. Experimental results show the high prediction accuracy of our SVP algorithm compared to Markov-chain and hidden-Markov model algorithms.