---
schema_version: "1"
id: 5d7e48856d59dfcde6b54562dcbe4cd41ee5c7238c51cebc70d6a6db7c4d4af3
title: Understand How Predictive Models Work in CSI Score
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/analytics/264-0-0/csi_score_predictive_understand.md
canonical_url: https://help.salesforce.com/s/articleView?id=analytics.csi_score_predictive_understand.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: 972e8f8c29130ef2a3f3244d5c5752a4b9ae1dbff284f9c981294f7181d37cf7
description: Before you start working with predictive models for CSI Score, learn about the predictive modeling assets of CSI Score installed in your org. Know the predictive modeling tasks completed during CSI Score installation and review AI Models resources to learn about predictive modeling in Data 360.
products:
  - Cross Cloud
release: "264"
---
# Understand How Predictive Models Work in CSI Score

Before you start working with predictive models for CSI Score, learn about the predictive modeling assets of CSI Score installed in your org. Know the predictive modeling tasks completed during CSI Score installation and review AI Models resources to learn about predictive modeling in Data 360.

### Required Editions

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small edition"><colgroup><col style="width:100%"></colgroup><tbody><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;"><a href="https://help.salesforce.com/s/articleView?id=analytics.csi_score_learn_requirements.htm&amp;release=264.0.0&amp;type=5" title="Learn about the Salesforce editions, products, and licenses required for CSI Score.">View supported editions</a></td></tr></tbody></table>

## Predictive Modeling Assets Available for CSI Score

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small ">
        <colgroup>
          <col style="width:33.33333333333333%">
          <col style="width:33.33333333333333%">
          <col style="width:33.33333333333333%">
        </colgroup>
        <thead class="slds-text-title_caps ">
          <tr class="">
            <th scope="col" class="slds-cell-wrap" style="vertical-align:top;" id="d4756e66">#</th>
            <th scope="col" class="slds-cell-wrap" style="vertical-align:top;" id="d4756e69">Asset</th>
            <th scope="col" class="slds-cell-wrap" style="vertical-align:top;" id="d4756e72">Purpose</th>
          </tr>
        </thead>
        <tbody>
          <tr class="">
            <td data-label="#" class="slds-cell-wrap" style="vertical-align:top;" headers="d4756e66 ">1</td>

            <td data-label="Asset" class="slds-cell-wrap" style="vertical-align:top;" headers="d4756e69 ">
              <ul>
                <li>Data model object (DMO): CSIScore Top Drivers Input</li>

                <li>Data stream: CSI Score DS</li>

              </ul>
            </td>

            <td data-label="Purpose" class="slds-cell-wrap" style="vertical-align:top;" headers="d4756e72 ">
              <p>This DMO and data stream consists of synthetic data used to train the
                predictive models for the composite scores.</p>
              <p style="margin-bottom:0;">When the data stream is created, the
                corresponding data lake object (DLO) is also generated to ingest the synthetic
                data before it is mapped to the DMO.</p>
            </td>

          </tr>
          <tr class="">
            <td data-label="#" class="slds-cell-wrap" style="vertical-align:top;" headers="d4756e66 ">2</td>

            <td data-label="Asset" class="slds-cell-wrap" style="vertical-align:top;" headers="d4756e69 ">
              <p>Regression type predictive models:</p>
              <ul>
                <li>CSIScore TopDrivers of VOC</li>

                <li>CSIScore TopDrivers of SENT</li>

                <li>CSIScore TopDrivers of JXS</li>

                <li>CSIScore TopDrivers of EES</li>

                <li>CSIScore TopDrivers of RHS</li>

                <li>CSIScore TopDrivers of OPS</li>

                <li>CSIScore TopDrivers of CHS </li>

                <li>CSIScore TopDrivers of CRI</li>

                <li>CSIScore TopDrivers of CLV</li>

              </ul>
            </td>

            <td data-label="Purpose" class="slds-cell-wrap" style="vertical-align:top;" headers="d4756e72 ">
              <p>These predictive models identify the top drivers for each composite score. The
                goal of the models is to determine which KPIs have the highest statistical leverage
                to make sure KPIs with the greatest potential to improve the composite scores are
                prioritized.</p>
              <p style="margin-bottom:0;">Synthetic data from the CSI Score Top Drivers Input DMO trains the
                models.</p>
            </td>

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

## Predictive Modeling Tasks Completed During CSI Score Installation

After CSI Score's predictive modeling assets are installed, the predictive models are trained with synthetic data. The initial model training with synthetic data doesn't consider any company-specific customizations. To train the models with your company's data and KPIs, retrain the models.

## AI Models Resources

 
| Resource | Purpose |
| --- | --- |
| [Key Concepts for Predictive AI](https://help.salesforce.com/s/articleView?id=data.c360_a_ai_predictive_about.htm&language=en_US) | Learn about the key concepts of AI Models and predictive modeling. |
| [Implementation Tasks for Predictive AI Solutions](https://help.salesforce.com/s/articleView?id=data.c360_a_ai_predictive_implement.htm&language=en_US) | Learn about the task involved in configuring a predictive model. |