Decision Support System for Reviewing Customer Churn Risk

The problem

In day-to-day operations, permitted usage, support and subscription records arrive through different systems and files, preventing the team from reviewing the same case in one view.

As a result, the link to source evidence can be lost while an explainable review priority is prepared, leading to repeated checks and uncertainty about the basis for the decision.

Incomplete automation may overlook a new account or seasonal usage, while incorrect automation risks inappropriate and overly forceful communication.

What we set out to improve

• Time taken for the explainable review priority draft to be ready for review
• Correct routing of records involving a new account or seasonal usage to the appropriate specialist queue
• Record of suggestions corrected or rejected by the customer success manager

How the system works

1. 01 Retrieve permitted usage, support and subscription records from authorised sources
2. 02 Verify the source system, record identifier and recency information
3. 03 Map the fields to the target process schema
4. 04 Prepare the explainable review priority draft
5. 05 Compare the draft with business rules and source records
6. 06 Check for an exception: a new account or seasonal usage
7. 07 Have the customer success manager approve, revise or reject the suggestion
8. 08 Write the input, suggestion, changes and final decision to the audit log

Methods we used

• Source-traceable data extraction for permitted usage, support and subscription records
• Structured output that limits the explainable review priority fields through business rules
• An exception gate that separates cases involving a new account or seasonal usage
• A queue that shows the customer success manager the source evidence and suggestion together
• Duplicate-processing controls and a reversal record to reduce the risk of inappropriate and overly forceful communication

Where people stay involved

Data and security

Only fields required for the task are processed from permitted usage, support and subscription records. Source-system permissions are preserved, and personal or commercially sensitive data is minimised before being passed to the model. Every read, suggestion, human change and write to the target system is logged.

Who this suits

Frequently asked questions