A Monetization Predictive Model for Marketing Campaigns on E-Commerce Service Platforms Based on Hidden Information

Organizations often deploy marketing campaigns on e-commerce service platforms to make profit. This paper presents a model for predicting the monetization rate of marketing campaigns run on e-commerce service platforms based on hidden information. Hidden information consists of two parts: user–campaign potential relations and implicit features. The relation data between entities (users and marketing campaigns) on the platform is complex and diverse, a new method called II2vec is used to represent the implicit information of user–campaign relations as vectors. To address the problem of incomplete true information of raw feature descriptions, a compressed interaction network (CIN) is used to extract valid implicit features and discover user-derived behaviors to further improve the model's learning performance. The proposed monetization prediction model (dynamic excitation convolutional neural network), which fuses the previous two kinds of hidden information, is able to analyze the force of campaigns on users while capturing local time-space features well, realistically depicts the psychological state of users at the edge of the purchase period, and dynamically simulates user's future behavior. The experimental results demonstrate that the model can both accurately predict the monetization rate of marketing campaigns run on e-commerce service platforms and reflect the multiple influence factors that drive the user purchase behavior.