# Customer Lifetime Value

BG/NBD-class probabilistic modelling that predicts high-value behaviour months ahead, integrated into Salesforce Marketing Cloud for automated segmentation.

## Key facts

- **Domain:** RETAIL & AVIATION
- **Status:** Delivered across multiple engagements
- **Use when:** Loyalty- or repeat-purchase-driven businesses want to shift from reactive to predictive marketing.
- **Reference engagement:** Available for new engagements

## The problem

Reactive marketing segments on what customers did last quarter. The campaign team needs to know what they will do next quarter, with the precision to reallocate spend.

## The approach

BG/NBD probabilistic models for repeat-purchase prediction, with optional ML overlays for cohorts where the baseline breaks (heavy promotion sensitivity, multi-product cross-sell).

## The architecture

Python modelling pipeline scoring per-customer CLV at a defined cadence. BigQuery as the data layer. Direct integration into Salesforce Marketing Cloud for segment activation.

## The outcome

A campaign team that targets future high-value behaviour, not past purchases. Segments refresh on the modelling cadence. The CFO can see the spend justification.

## ATI shape

- Predictive intelligence — BG/NBD-class probabilistic CLV per customer
- Agentic execution — Scheduled scoring + automated segment refresh
- Secure data — BigQuery + scoped service accounts to Marketing Cloud
- Actionable outcomes — Activated segments inside the marketing cloud

## Tech stack

- Python
- BigQuery
- BG/NBD
- Salesforce Marketing Cloud

## Impact

- Forward — Score future behaviour, not past purchases
- Probabilistic — Defensible uncertainty estimates
- Activated — Segments push into Marketing Cloud automatically

## Related

- [All accelerators](https://levent.ai/accelerators/)
- [Next: Ekam](https://levent.ai/accelerators/ekam/)

Metrics on this page are estimated and expected improvements describing the design intent of the accelerator. Real-client delivered metrics stay in private decks; see https://levent.ai/ai-content-policy/ for the abstraction policy.

---

**Canonical URL:** https://levent.ai/accelerators/clv/