NEED HELP ?

Too much data and not enough time and resources to leverage it intelligently? Need someone to assist you in decision-making by mining the data you have on your Customers, Products, Employees or Operations? Have an urgent need for sophisticated data analytics? Or just plain data management? Get a 2-pager on us. And contact us .

June 11, 2013

Managing Online Transaction Fraud

Managing online fraud continues to be a significant and growing cost for online merchants of all sizes and industries - primarily E-Commerce, payments and remittances.


Our client - a leading service provider of online remittances had significant opportunities for fraud and money laundering. They did not have an automated transaction screening system; most of their transactions were reviewed manually for fraud and compliance guidelines.

A lot of time was invested in manual review of all transactions, which in turn delayed transaction processing time and also impacted Customer Satisfaction.  They needed a solution to optimize their fraud management process by reducing cost and transaction processing time.


We developed a predictive model outputing a 'Risk Score' and a 'Risk Class', and related business process wherein only high risk transactions were sent for manual review, and rest approved automatically. A schedule of data extraction was setup to generate the Risk score before KYC forms were prepared.  The process was streamlined to ensure that all KYC forms carried a Risk score and Risk Class.  The Compliance committee continues to give it’s opinion on each KYC form (Low Risk to Extremely High Risk) and the predictive model continues to be bootstrapped.


KYC Form - Illustration

The new process reduced number of transactions reviewed manually from 700-800/day to 200/day, and also reduced the average turnaround time for transactions from from 3.0 to 1.5 days.  Thereby reducing cost and improving Customer Satisfaction.

More details can be found here.

No comments: