With business getting an overwhelming response, customer debts started to grow exponentially and associated recovery was always a challenge at an overall level, the company had been storing a large volume of relationship data points for a long time but none of this could be put to use to calculate the risk score. This resulted in the collections department being handicapped on recovery of certain bad debts.


He Data warehousing team at this big financial services company analyzed large sets of customer records collected from sources such as Loan management systems and credit bureau data. The data warehouse architecture involved ingesting all data into a OLAP database, performing a human intervention to calculate and speculate a “Risk Profile” and loading them into the final master

How did Whiteklay come over the challenges

The IZAC analytical framework deployed on Hadoop architecture revolutionised the build of a Customer risk profiling use case with just 15 node distributed computing setup. The solution utilized the power of Hadoop over Spark computing and Machine learning processing framework to evolve a system which could auto profile a customer and calculate a risk score associated with the same.