---
schema_version: "1"
id: 661bcbc1b36a7583fb17639df756ab28482f0b5bc0fa73333a1533ef949b8540
title: Key Terms 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_learn_terms.md
canonical_url: https://help.salesforce.com/s/articleView?id=analytics.csi_score_learn_terms.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: 77c47657b8ed10b10c6aa7b3680874a0f22105eb7eb84066cecb1c08dd66c774
description: Familiarize yourself with the core terminology used in Customer Signals Intelligence (CSI) Score.
products:
  - Cross Cloud
release: "264"
---
# Key Terms in CSI Score

Familiarize yourself with the core terminology used in Customer Signals Intelligence (CSI) Score.

### 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>

## Data Architecture

Data Model Object (DMO)

The container within Data 360 where raw signals and customer data from disparate sources are grouped and stored.

C360 Semantic Model

The foundational data layer in Tableau Next that ingests and structures customer data from Data 360 DMOs. It establishes the necessary relationships between different data objects (DMOs) to create a unified, query-ready dataset before any scoring logic is applied.

CSI Score Semantic Model

The analytical layer that sits on top of the C360 model to apply specific business logic. It contains the definitions for metrics, calculated fields, and parameters used to compute the normalized individual KPI scores and the all-up CSI score.

Logical Views

Virtual tables within the CSI Score semantic model that join multiple DMOs to simplify score calculations.

## Calculation Logic

Normalization

The process of standardizing different data units such as percentages, currency, and counts onto a common 0–100 scale so they can be compared and aggregated accurately.

Weighting

The assigned importance of a specific KPI in the overall calculation. This allows the model to prioritize high-impact metrics over lower-impact ones.

Composite Score

A single score is derived from combining multiple individual indicators by using a weighted average.

## Scores

All-Up CSI Score

The top-level composite score that provides a unified view of overall customer and business health.

Composite Score

The specific score for a distinct performance area such as customer engagement that feeds into the final composite score.

KPI

The foundational metrics such as CSAT and mobile bounce rate that measure specific aspects of performance. These individual metrics roll up to calculate the composite scores.

## AI

SHAP Values

Values that quantify the global impact of specific KPIs across the company, providing transparency into the AI model's calculations.

Top Drivers

The specific KPIs identified by predictive models as having the highest statistical leverage to improve a composite score.

Gradient Boosting Machine (GBM)

The underlying AI model used by CSI Score to analyze complex data relationships and identify score drivers.

Synthetic Data

The placeholder data used to initially train the predictive models during installation, which is later replaced when a company retrains the model with its own data.