Agentic Personalisation of Cross-Channel Marketing Experiences
This addresses the challenge of automating and personalising marketing communications for large-scale consumer applications, though it is incremental as it builds on existing methods like Thompson sampling.
The paper tackles the problem of manual, labor-intensive orchestration of cross-channel marketing communications, which hinders effective personalisation. It presents a sequential decision-making framework using Difference-in-Differences and Thompson sampling, resulting in significant increases in goal events across product features and deployment to 150 million users.
Consumer applications provide ample opportunities to surface and communicate various forms of content to users. From promotional campaigns for new features or subscriptions, to evergreen nudges for engagement, or personalised recommendations; across e-mails, push notifications, and in-app surfaces. The conventional approach to orchestration for communication relies heavily on labour-intensive manual marketer work, and inhibits effective personalisation of content, timing, frequency, and copy-writing. We formulate this task under a sequential decision-making framework, where we aim to optimise a modular decision-making policy that maximises incremental engagement for any funnel event. Our approach leverages a Difference-in-Differences design for Individual Treatment Effect estimation, and Thompson sampling to balance the explore-exploit trade-off. We present results from a multi-service application, where our methodology has resulted in significant increases to a variety of goal events across several product features, and is currently deployed across 150 million users.