/ portfolio /
Recommendation and decisioning systems.
Recommendation systems only matter when they improve customer experience and business outcomes. This page tracks my portfolio around product recommenders, next-best-action systems, search relevance, churn prevention, and personalisation measurement.
What this will demonstrate
Business framing
How to connect recommendations to conversion, retention, average revenue per user, lifetime value, and customer usefulness.
System design
Candidate generation, ranking, feedback loops, cold start, eligibility rules, and operational constraints.
Decisioning
Next-best-action logic across CRM, ecommerce, content, lifecycle marketing, and churn prevention.
Measurement
Offline metrics, online experiments, incrementality, guardrails, and long-term learning loops.
Planned assets
- Product recommender case study template.
- Next-best-action architecture note.
- Churn prevention as a decisioning system.
- Vertex AI Search for ecommerce: where it fits and where it does not.
Recommended next
Keep reading from this thread
From 500 indexed pages and articles.
- Wiki concept AI Decisioning Learning-based marketing personalisation where AI agents decide which experience to deliver to each customer, optimising toward defined business goals within explicit Related by decisioning
- Wiki concept Community Of Bandits A community of bandits is Braze's AI decisioning architecture for splitting a large marketing action space into collaborating contextual bandits, each responsible for Related by decisioning
- Wiki concept Agentic Marketing A learning-based marketing operating model where AI agents continuously experiment across multiple experience variables for individual customers, instead of marketers manually Related by decisioning