# Predict Campaign Profit

Click on the Prediction Tab in the top right corner of your screen.

From the dropdown Menu, choose the Model you wish to create a Prediction for.

<figure><img src="/files/gnsywMkaoi5ILzUdfiwg" alt=""><figcaption></figcaption></figure>

#### Enter Commercial Data

* Click on the Edit button in the Header.
* Give your Selection a meaningful name.
* Enter Contact Cost. This is the Cost per Customer contact, for example, in a Print Campaign this can be the cost of printing and shipping Marketing Material per Customer.
* Enter Overhead Cost. This is the sum of all One-time costs for the Campaigns, for example, the design cost of the Marketing Material.
* If your Prediction optimizes for Conversion rather than Revenue, enter Average Order Value. This is the mean amount paid by customers for an Order.
* Enter Average Profit Margin. This helps the Predictions Platform understand how much revenue turns into Gross Profit.
* Scroll to the bottom of the Edit Window and click 'Apply' to save the commercial data for the **current** prediction. Alternately, you can click the Save button next to the Commercial Data; This saves the data for **all** predictions.

<figure><img src="/files/RKezFHiLnzjjule8WbXZ" alt=""><figcaption></figcaption></figure>

#### Make a Selection

* To automatically set Optimum Selection Size, click on "Optimize for Profit". YOu can see the number of the customers present in the Optimal Selection.
* Optionally, deselect "Optimize for Profit", and manually enter the preffered number of customers for the Campaign.
* Click Export.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://documentation.crossengage.io/predictions-platform/tutorials/predict-campaign-profit.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.