Combing Customer Profiles for Members’ Return Visit Rate Predictions

The major profit of portal companies in Taiwan is generated by online advertising and e-commerce. Effective advertising requires predicting how a user responds to an advertisement and then targeting (presenting the advertisements) to reflect users’ favor. As customers’ preferences may change over time, we take the different types of past behavior patterns of the registered members to capture concept drifts. Then, we combine the click preference index (CPI) and the preference drifts to propose a Behavioral Preference (BP) model, and to predict the members’ return visit rates in the specific category of the portal site. The marketers of the portal site can target the registered members with high return visit rates and design corresponding marketing strategies. The experimental results with a real dataset show that our model can effectively predict the registered members’ return visit rates.