---
title: Execute ML Model
description: Execute a trained machine learning model on input data.
category: Infoveave Activities
tags: [ml, model execution, prediction, machine learning, trained model]
---

# Execute ML Model

## Description

The **Execute ML Model** activity allows you to apply a trained machine learning model (previously created and stored) on the selected dataset. The model can perform predictions, classifications, or other ML-based tasks depending on its type and training.

Use this activity to:

- Run a trained model on live or batch data
- Generate predictions or decisions based on model logic
- Integrate ML results into workflow pipelines for automation or analysis

> **Use Case**:  
> In a loan approval pipeline, this activity can run a model trained on customer financial data to predict creditworthiness. In a retail scenario, it may classify customer feedback as positive/negative or detect fraud patterns.

---

## Input

_Not Applicable_

---

## Output

| Type | Description                                          |
| ---- | ---------------------------------------------------- |
| Data | Model output, such as predictions or classifications |

---

## Configuration Fields

| Field Name       | Description                                                         |
| ---------------- | ------------------------------------------------------------------- |
| **ML Model**     | Select a trained machine learning model from the ML model registry. |
| **Model to use** | Optional alias or reference name for the model being executed.      |

---

## Sample Input

_Not applicable_ — input is pulled from the specified data source.

---

## Sample Configuration

| Field        | Value                       |
| ------------ | --------------------------- |
| ML Model     | `Loan_Default_Predictor_V3` |
| Model to use | `LoanModel`                 |

---

## Sample Output

| CustomerId | CreditScore | Predicted_Default |
| ---------- | ----------- | ----------------- |
| 123        | 750         | No                |
| 124        | 520         | Yes               |
| 125        | 690         | No                |