---
schema_version: "1"
id: 0c9750f6b6b34c953094d833fe55075cb7db94f21a60030e447954714f23bf31
title: Configure Einstein Decisions
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/mktg/264-0-0/mc_pers_einstein_decision_configure.md
canonical_url: https://help.salesforce.com/s/articleView?id=mktg.mc_pers_einstein_decision_configure.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: 4db0bc00aa8d9fe6ab549edcbca54e7059509271dc6cf48fd4997a833fd32636
description: Einstein Decisions analyzes many unique data points when determining the right experience to present to a particular user. This data includes user behaviors as well as contextual data, such as device type, time of day, and demographic data. Einstein Decisions can also reference segment membership and user attribute data, along with catalog objects you create in your catalog. To determine which data Einstein Decisions references, you define the machine learning features on the Feature Engineering page. Typically, a data science or analytics team member configures the feature engineering options for Einstein Decisions.
products:
  - Marketing
  - Salesforce Personalization
release: "264"
---
# Configure Einstein Decisions

Einstein Decisions analyzes many unique data points when determining the right experience to present to a particular user. This data includes user behaviors as well as contextual data, such as device type, time of day, and demographic data. Einstein Decisions can also reference segment membership and user attribute data, along with catalog objects you create in your catalog. To determine which data Einstein Decisions references, you define the machine learning features on the Feature Engineering page. Typically, a data science or analytics team member configures the feature engineering options for Einstein Decisions.

### Required Editions

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small edition"><colgroup><col></colgroup><tbody><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;">Available in: Premium edition</td></tr></tbody></table>

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small permission">
        <colgroup>
          <col style="width:50%">
          <col style="width:50%">
        </colgroup>
        <thead class="slds-text-title_caps ">
          <tr class="">
            <th scope="colgroup" class="slds-cell-wrap" colspan="2" style="text-align:center;vertical-align:top;" id="d95109e54">Permissions
              Needed</th>
          </tr>
        </thead>
        <tbody>
          <tr class="">
            <td data-label="Permissions Needed" class="slds-cell-wrap" style="vertical-align:top;" headers="d95109e54 ">To configure Einstein Decisions:</td>

            <td class="slds-cell-wrap" style="vertical-align:top;" headers="d95109e54 ">A role with Contextual Bandit Create/Edit permissions</td>

          </tr>
        </tbody>
      </table>

1. From the **Machine Learning** section of the main navigation, select **Einstein Decisions** | **Feature Engineering**.
2. Select the training target from the **Bandit Target** dropdown—**Click**, **Conversion**, or **Goal Completion**.
3. Select the features you want to use while training the machine learning models.
4. To include specific user segments, click **+Segment** in the **Segment Membership** section and select options from the dropdown.
5. To include specific locations, click **+Geography** in the **Geography** section and select options from the dropdown.
6. To include custom attributes, click **+Attribute** in the **Custom Attribute** section and select options from the dropdown.
7. To include recent user actions with catalog objects, click **+Catalog Object** in the **Catalog Object Interaction History** section and select options from the dropdown.
8. Click **Save**.
    
    After configuring the training target and feature engineering options, you can create campaigns with promotions that use Einstein Decisions.