In early 2015 Card Limited approached us with a problem. They had recently acquired a new prepaid debit card portfolio. The portfolio had solid bottom line numbers and performance that made it an attractive acquisition, but the previous owners had not provided any detailed data regarding customer value and performance.
A few months after acquiring the portfolio they realized that there was the potential for a sizeable, unidentified population of fraudulent users. They had three questions:
- What can we do to programmatically identify fraud as it occurs?
- What percentage of our overall portfolio is composed of fraudulent members?
- Of the non-fraudulent users, what initial behaviors would predict towards a higher lifetime value for Card.