Agentic Personalisation of Cross-Channel Marketing Experiences

2025-06-19

AI Summary

Manual orchestration in cross-channel marketing leads to insufficient personalization in content, timing, frequency, and copy. Method: This paper proposes an agent-driven, causally enhanced sequential decision-making framework. It introduces a novel strategy optimization mechanism integrating Difference-in-Differences (DID) causal effect estimation with Thompson sampling, enabling interpretable and scalable personalized decisions; and designs a modular policy network supporting joint modeling and coordinated optimization across multi-touch channels—including email, push notifications, and in-app messaging. Contribution/Results: Evaluated in a production environment with 150 million users, the system significantly improves incremental engagement rates across all funnel stages and boosts target-event conversion rates. It establishes a new paradigm for large-scale, causally grounded personalized marketing.

Technology Category

• Reasoning under Uncertainty: Sequential Decision Making
• Search and Optimization: Learning to Search
• Machine Learning: Causal Learning

Application Category

• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

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.

Problem

• Optimize cross-channel marketing personalization automatically
• Reduce manual marketer work in content orchestration
• Balance exploration-exploitation in engagement strategies

Innovation

• Sequential decision-making framework for engagement optimization
• Difference-in-Differences for Individual Treatment Effect estimation
• Thompson sampling to balance explore-exploit trade-off