Data-Driven Personalization and AI

This unit explores how internal and third-party customer data are prepared, evaluated, and ethically used to drive personalization at scale. Students examine personalization approaches—from traditional methods to contemporary and generative AI—consider contextual constraints, customer types (consumer vs. non-consumer), and design end-to-end solutions that improve routing, agent support, and customer satisfaction using real-world examples.

Learning Objectives

• Analyze internal and third-party customer data sources and assess data quality, completeness, and suitability for use in personalization and AI-driven pipelines
• Evaluate ethical, privacy, and regulatory considerations when collecting and using customer data and propose mitigation strategies for responsible personalization
• Compare and differentiate personalization model types (rule-based, collaborative, content-based, hybrid, and generative AI) and select appropriate approaches based on customer type, context, and business goals
• Design a contextual personalization workflow that integrates model selection, generative AI components, automated message routing, and agent support to improve customer experience and measurable satisfaction metrics