Building a Mobile Personalized Marketing system using multidimensional data

Mobile marketing can be made more personalized through Mobile Personalized Marketing (MPM). To personalize the content, the information regarding the customers need to be captured more in detail such as customer location, age and gender. This customer information can be collected using Smartphone which is rising in the marketing industry. This will help in getting all the information of user to push the advertisement in a more personalized way. In this system, we mainly focus on the multidimensional data collected from the user to analyze the user activity from multiple perspectives and push the advertisement in a personalized form. The existing work focuses on the contexts of mobile users and their activities, which will provide prediction of customer preferences. The existing system considers only a limited number of dimensions in predicting the user preferences, which may not accurately predict users behavior and this is an obstacle to get accurate data. The proposed work focuses on increasing the number of dimension combination for each event with the user context and activities. User clustering is constructed and similarities between the users are also evaluated for predicting the user behaviors. Personalized Marketing refers to target an individual customer based on their interest towards product or services. So, multiple dimensions can be used to push more personalized marketing products and services based on the user context and action events.