---
title: "Measure your current model's performance against a target segment"
slug: "measure-your-current-models-performance-against-a-target-segment"
updated: 2024-10-23T00:24:16Z
published: 2024-10-23T00:24:16Z
canonical: "help.madkudu.com/measure-your-current-models-performance-against-a-target-segment"
---

> ## Documentation Index
> Fetch the complete documentation index at: https://help.madkudu.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Measure your current model's performance against a target segment

### **Prerequisite**

- You have the Architect or Admin permissions

**Objective**:

Running a quick check of your model's performance on a new customer segment (in Madkudu, this is called an Audience). Examples: different geographies, industries, or product line. This is useful if you want to have a glimpse before modifying your model.

**Step-by-step guide**:

1. If this segment doesn't yet exist in Madkudu, create a [new Audience:](/v1/docs/audience-mapping)
  - Access the Audience Mapping in the app (App > Mapping > Audience Mapping).
  - Create an audience with the right filters. If you don't see a particular field from an object, please make sure you have [pulled the field](/v1/docs/how-to-pull-additional-fields-to-use-in-the-madkudu-platform). Access this by looking at Integrations > Connector > Pull.
  - Wait for the new audience processing to be completed (this typically takes 24hours).
2. Check the performance:
  - Once the audience has been created, go to App > Predictions > Customer Fit.
  - Select your audience in the top-left corner, then look at the performance charts below.
  - Determine whether you want to update your model, create new models or do nothing :)

Unsure what to look at when evaluating performance? Check out [Recall and Precision: how is the performance of a prediction model measured?](/v1/docs/recall-and-precision-how-is-the-performance-of-a-prediction-model-measured)

-