# Using Model Created on Exchange Machine Learning

**URL:** <https://forum.inductiveautomation.com/t/using-model-created-on-exchange-machine-learning/115005>\
**Category:** Ignition Exchange\
**Created:** [April 10, 2026, 2:16pm UTC](https://forum.inductiveautomation.com/t/using-model-created-on-exchange-machine-learning/115005 "2026-04-10T14:16:58Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![kennethandradeom](https://avatars.discourse-cdn.com/v4/letter/k/3e96dc/32.png) [@kennethandradeom](https://forum.inductiveautomation.com/u/kennethandradeom)\
**Post date:** [April 10, 2026, 2:16pm UTC](https://forum.inductiveautomation.com/t/using-model-created-on-exchange-machine-learning/115005/1 "2026-04-10T14:16:59Z")

</div>

I’ve created a model to calculate future points in Ignition Exchange Machine Learning. The model is already tested and everything, but I need to call it from another application. Is this possible?

I configured the model call through the Gateway Scripts on my gateway, but I get an error when trying to call the Exchange. What function should I use to be able to call it?

The model was trained using polynomial linear regression and is already done I just want to call it and see a prediction of the next 10 future points. Is the model Presion Tanque Pulmon

Thanks in advance.

 ![image](https://us1.discourse-cdn.com/inductiveautomation/original/3X/5/f/5f67bd4d03f62983b3b699703f5c933dc61104f0.png)

---

<div class="post-metadata">

**Author:** ![Matrix\_Engineering](https://sea1.discourse-cdn.com/inductiveautomation/user_avatar/forum.inductiveautomation.com/matrix_engineering/32/19781_2.png) [@Matrix\_Engineering](https://forum.inductiveautomation.com/u/Matrix_Engineering)\
**Post date:** [April 10, 2026, 3:07pm UTC](https://forum.inductiveautomation.com/t/using-model-created-on-exchange-machine-learning/115005/2 "2026-04-10T15:07:44Z")

</div>

> [@Ignition with Machine Learning](https://forum.inductiveautomation.com/t/ignition-with-machine-learning/114993):
>
> Hi, my name is Kenneth, I am working with Ignition Machine Learning Manager and I have historical tag data (temperature and humidity) collected over several months. My goal is to build a model that can predict future values (for example, predicting temperature 10 minutes ahead) based on current and past data. Currently, I am able to: Retrieve tag history data Train a regression model (OLS Multiple Linear Regression) However, I am unsure about the correct way to structure the dataset f…

You have already been warned about multiple topics. Reply to your other thread.

---

<div class="post-metadata">

**Author:** ![nminchin](https://sea1.discourse-cdn.com/inductiveautomation/user_avatar/forum.inductiveautomation.com/nminchin/32/6911_2.png) [@nminchin](https://forum.inductiveautomation.com/u/nminchin)\
**Post date:** [April 27, 2026, 3:52am UTC](https://forum.inductiveautomation.com/t/using-model-created-on-exchange-machine-learning/115005/3 "2026-04-27T03:52:01Z")

</div>

I feel this is different to the other surviving post, it's asking about accessing it outside of Ignition, having machine learning already working