E-commerce & Digital
Customer lifetime value prediction
Predict the future value of each customer based on purchase history, engagement patterns, and demographic signals. Use CLV predictions to allocate marketing spend and prioritise retention efforts.
10–25%
improvement in marketing spend efficiency
Opportunity assessment
Moderate impact. Meaningful cost or revenue improvement, likely noticeable at function level but modest relative to total business scale.
Moderate effort. Requires configuration, prompt engineering, and testing. A capable team can get there but expect several months.
Demanding data requirements. Relies on clean, integrated data across multiple systems. Significant data preparation work typically needed.
Low risk. Limited external exposure. A human reviews output before it reaches anyone outside the team.
Moderate people impact. Part of someone's working day changes. Requires training and some adjustment time, but roles remain broadly the same.
Tooling required
Things to consider
CLV prediction requires at least 12–18 months of transaction history per customer to produce meaningful predictions. For new customers, proxy signals (acquisition channel, first-order characteristics) can provide early estimates.
The model's value comes from differential treatment — spending more to retain high-CLV customers and less to win back low-CLV customers. Without changing the marketing allocation based on predictions, the model is academic.
CLV is a prediction, not a fact. Communicate it as a probability-weighted estimate and resist the temptation to treat it as a precise number — false precision leads to bad decisions.
Experiment starter: Segment your existing customers by total spend over the last 2 years. Identify the top 10% and bottom 50% by value. Compare their first-order characteristics (channel, category, order value, discount usage). If clear patterns emerge, you have a foundation for a predictive model.
Go deeper in the playbook
Section — Opportunity Identification, including the AI Opportunity Assessment ScorecardSection — RAG and Knowledge Systems: Unlocking Proprietary DataThis is an decision support opportunity — see the relevant playbook section for how to approach it.More in E-commerce & Digital
Product categorisation at scale
Automatically assign products to the correct site taxonomy categories using title, description, and attributes. Removes a bottleneck on new product onboarding.
Site search query analysis
Analyse search queries for intent, gaps, and failed searches. Identify where customers can't find what they want and prioritise catalogue improvements.
A/B test copy generation
Generate multiple headline, CTA, and banner copy variants for testing. Covers different value propositions, tones, and lengths with a single brief.
AI Transformation Playbook
Ready to assess your own opportunities?
The playbook gives you the full 150-opportunity directory, scoring tools, and 100+ templates for every stage of an AI transformation programme.