Set Up Invoice Risk Scoring to Predict Risk Scores for Invoices (Pilot)
A risk score for an invoice predicts the likelihood that payment for an open invoice is
delayed beyond its due date. The score estimates the probability of late payment based on
patterns and signals such as historical payment behavior, invoice aging, outstanding balances,
customer payment trends, dispute history, and other relevant account
characteristics.
Note Invoice Risk Scoring is a pilot or beta service that is subject to the Beta Services Terms
at Agreements - Salesforce.com or a written Unified Pilot Agreement if
executed by Customer, and applicable terms in the Product Terms Directory. Use of this pilot or beta
service is at the Customer's sole discretion.
The risk score helps billing and finance teams identify invoices potentially requiring closer
monitoring, and it helps them prioritize collection efforts. A higher risk score indicates a
greater likelihood of overdue payments, while a lower score suggests payment is more likely on
or before the due date.
By incorporating risk scores into collections workflows, organizations can improve collection
efficiency, reduce overdue receivables, and better manage cash flow. For example,
organizations can route invoices with higher risk scores to specialized collection plans,
assign invoices to collection reps for proactive outreach, or include them in targeted
reminder campaigns before the due date. Lower-risk invoices can follow standard collection
processes so teams focus their efforts on accounts that require immediate attention.
Turn On Legacy AI Model Creation (Pilot) Legacy AI Model Creation allows the system to create predictive AI models with the appropriate runtime configuration required for invoice risk scoring.
Configure Scoring Framework (Pilot) Use the prebuilt Scoring Framework configuration template type to install and configure the scoring app. This app creates and trains the Predictive AI model to project invoice risk levels.
Configure the Scoring Framework Template (Pilot) After you configure the scoring framework template, set up the predictive AI model by defining the data space, training data, risk score thresholds, and input features.
Schedule Data Transform for Scoring (Pilot) After successfully installing the Invoice Risk Scoring app, schedule the data transform to compute risk scores on your latest open invoices.
Create Use Case for AI Accelerator (Pilot) After configuring the Scoring Framework and creating the Copy Field Enrichment, create and configure a machine learning use case in AI Accelerator. The AI Accelerator use case connects the trained Invoice Risk Score model to your Salesforce org so that risk predictions are accessible on invoice records.
Did this article solve your issue?
Let us know so we can improve!
Loading
Salesforce Help | Article
Cookie Consent Manager
Cookie Consent Manager
General Information
Required Cookies
Functional Cookies
Advertising Cookies
General Information
We use three kinds of cookies on our websites: required, functional, and advertising. You can choose whether functional and advertising cookies apply. Click on the different cookie categories to find out more about each category and to change the default settings.
Privacy Statement
Required Cookies
Always Active
Required cookies are necessary for basic website functionality. Some examples include: session cookies needed to transmit the website, authentication cookies, and security cookies.
Functional Cookies
Functional cookies enhance functions, performance, and services on the website. Some examples include: cookies used to analyze site traffic, cookies used for market research, and cookies used to display advertising that is not directed to a particular individual.
Advertising Cookies
Advertising cookies track activity across websites in order to understand a viewer’s interests, and direct them specific marketing. Some examples include: cookies used for remarketing, or interest-based advertising.