---
title: What is Real-time decisioning?
url: https://markin.ai/glossary/real-time-decisioning
category: Decisioning and next best action
---

# Real-time decisioning

> Real-time decisioning evaluates a customer's current context and returns an action within the latency budget of the moment, typically tens of milliseconds inside an app or call. It matters where intent is perishable, and it is deliberately unnecessary where it is not.

## Why it matters for ARPU

Not every decision needs to be instant, but the ones triggered by intent, failure or friction lose most of their value if they arrive the next day.

## Related terms

- [Next best action](https://markin.ai/glossary/next-best-action), Next best action is the single intervention that maximises expected value for a specific customer at a specific moment, chosen across every available option including doing nothing.
- [Decision layer](https://markin.ai/glossary/decision-layer), A decision layer is the system that sits between the data warehouse and the execution tools and decides, per customer, what deserves to happen next.
- [Feature store](https://markin.ai/glossary/feature-store), A feature store computes, versions and serves the model inputs used in training and in production, guaranteeing that both see the same definition of a feature.
- [Decision volume](https://markin.ai/glossary/decision-volume), Decision volume is the number of distinct, evidenced customer-level decisions a business makes in a period.

## Go deeper

- [Customer decisioning](https://markin.ai/solutions/customer-decisioning), Latency tiers by use case.
- [Integrations](https://markin.ai/integrations), Where decisions are delivered.

Source: https://markin.ai/glossary/real-time-decisioning