Optimising debt collection efforts for over 1 million cases
Hello
with the
implementation of a cloud-based debt prioritisation solution
“ The solution helped us to work
the right cases first and reduce
the time taken to work a case
by more than 50% ”
Head of Debtors Shared Services - Quote is paraphrased
Case Study
Industry
Health Care
Company Size
10,001+ employees
Problem Space
Predictive Analytics
Azure
Insights
Machine Learning
Debt Collection
Technology Used
Python
AzureSQL
AzureVNet
AzureDataFactory
AzureMachineLearning
Business Context
Thousands of medical cases are processed by large healthcare providers each day. The majority of these cases
need to be settled through medical aids or privately by the patients themselves. Often cases can take up to
3
years to finalise. This is an area that had significant potential to improve through data-driven solutions
and
automation.
Challenge
Improve debt collection efficiency on
thousands of bills not paid each day
The current process prioritises collection
efforts based on value outstanding only.
High number of physical and digital touch
points involved in the billing process resulting
in errors and omissions costing millions.
Solution
An Azure-based debt prioritisation
solution to process thousands of cases
each day
Implemented a data consolidation strategy to
create visibility of cases and actions taken
across multiple source systems.
Created a PowerBI dashboard to prioritise and
manage debt collection efforts on a daily basis.
Automated Debt
Prioritisation Solution
Reduced time to action outstanding cases and
improved collection revenue
💰
Over 1 million cases prioritised to
approximately 10k with the
highest likelihood of collection
🕑
~50% reduction in time taken to
work a prioritised case
🚀
Increased visibility of cases across
debt, medical and finance
systems
