Preemptive Money Laundering for a large US bank
Overview.
The client’s collections department handles different products such as credit cards, mortgages, loan, overdraft etc. 100k bank accounts get scanned/month, where 6-7k defaulters are identified/month. Here, mode of repayments could be CS, auto payments through saving accounts or cheque. This client needed a more robust collections system that can adapt to the complexities of modern financial crime.
Challenges.
Ever increasing AML activities and decreasing detection rates
Traditional clustering using KYC details and behavior patterns
Customers are complex entities and need continuous monitoring for anomalous behavior
Transaction rules are not sufficient
Solution.
Identify important data points: Demographic, Transactions, Balance Data
Using Coforge’ s in-house AI accelerator, aggregate data and build customer clusters
Each customer is a mixture of prototypes of clusters. Soft clustering behavioral misalignment score is generated.
Suspicious customers are:
not in any cluster
misaligned within the clusters
deviate from the cluster prototype
Also, magnitude of the delay for payments to be received is estimated.
The Impact.
Pre-empt the collection process
Early detection of risky collections
Increase recoveries
Improve customer churn
Minimizing operational cost
Efficient fraud management
Improvement in fraud detection rates
Significant fall in false positives
Effective workload management
Reduced manual intervention
Bring us your challenge.
Let’s Coforge your next success story.
Your browser does not support the video tag.
WHAT WE DO.
Explore our wide gamut of digital transformation capabilities and our work across industries.
Explore
.jpeg?length=1920&name=HB%20Item%201%20(31).jpeg)
