Condé Nast: Representation Learning for Modeling and Predicting User Engagement and Propensity for Conversion Through the Engagement Funnel

Project Description

PI: Nitesh V. Chawla; co-PI: Meng Jiang

A digital convergence is incomplete without a data convergence. As Conde Nast embraces a more digital engagement platform with its wide consumer base, it opens up important monetization questions around content, subscription, as well as the product offerings that may be available via the digital platform. The fundamental challenge remains: What do we know about our consumers to take them through the engagement funnel? Imagine a user coming from the wild -- not a subscriber -- what can we infer about that user to infer the intent to either convert to a subscription? Subsequently, what can we infer about the subscriber to convert to product purchase off the platform? Irrespective, granular level information about the consumer -- driven from the content engagement --- can help drive more accurate market segments for advertisements. There is a potential to achieve a significant increase in ROI by modeling and understanding the consumer through the engagement and conversion funnel.


Email: mjiang2 [at]

Graduate Student

Daheng Wang: PhD student (2016-), co-advised with Dr. Nitesh Chawla
Email: dwang8 [at]
Representation learning: Complementarity learning and graph neural networks