Debt Management and Collection Analytics

Debt management and collection is one of the core functions of any financial institution that has some outstanding payment with consumers. Due to increasing competition, easy accessibility of credit to consumers and increasing pressure from the regulatory bodies to be consumer sensitive, Debt collection agencies are changing their approach to be more and more consumer centric. The companies are realigning their strategic approach to take a consumer centric view and shifting the focus of organizations to provide better consumer service along with the goal of profit maximization.

Traditionally, collection starts when the consumer fails to clear his monthly dues, but with the availability of information about consumers and advanced techniques of data analytics, collection process starts much before the actual default. Usually collection activity is initiated proactively at the time when sign of delinquency occurs much before actual default. The companies usually have at least updated demographics about the clients (as they contact consumers time to time), billing information and their payment behavior (automatically generated in the system). This data can be used to predict the consumer's paying ability and to calculate their propensity to default in next billing cycle. It will also help companies in understanding the consumer requirements and develop consumer centric approach. The consumer intelligence is also applied to identify low risk consumers to target them with credit increase or other cross sell opportunities. The idea is to develop strategy balancing practical operational constraints and consumer satisfaction.

Pre–Delinquency period:

The objective in pre-delinquency is to minimize the default in active and current (0 Days Past Due) portfolio.

Usually collection starts only after the default by the consumers but application of predictive analytics helps to identify the risky consumers much before the actual default. The consumer starts showing the typical sign indicating higher propensity of default before actual delinquency. Predictive model helps the companies to identify these consumers proactively and work with them to avoid default. Usually signs like bureau data deterioration, worsening behavior score shows that the consumer is over-indebted and defaulting on others lender accounts. Unusual transaction pattern like rapid increase in credit line usage might be a sign of runaway spend or fraud. The companies gather consumer intelligence using different consumer segmentation techniques and regression analysis. The companies use predictive analytics to develop a mechanism to raise early warning alert on time and take measures to reduce risk exposure to such activities.

The strategic approach at pre delinquency is very critical as consumer has not done anything that is contractually wrong. Besides it, in early delinquency stage a significant chunk of consumer are good consumers who are just revolvers and missed their payment unintentionally. The revolvers are very profitable consumers who usually miss payment on time but pay back with late fine or interest charges. The companies prefer to segment these consumers and treat them differently. The best approach is to do consumer segmentation over consumer base and investigate the reasons of default. This also helps the companies to understand their consumer better and improve their processes to help the consumers and avoid likely default.

Another way which is very effective and easy to implement is the “Early Warning Delinquency Scorecard”. A predictive model can be built using information about consumer, his paying and billing information. The output of the model will be ordered score such that higher the score greater the chances of the default of the consumer in next billing cycle. The score could be used directly to segment the consumer for differential treatment. The consumers with higher risk could be followed up with polite reminder calls. The output of the scores can be combined with the consumer segmentation to identify the usual revolvers or Runaway Spend or Frauds proactively.

ScoreData Advantage:

ScoreData advocates the adaptation of data analytics in the pre-delinquency stage itself. It provides more time to companies to act and opportunity to prevent delinquency proactively. Our predictive solutions segment the consumers using their demographics, collection data and also do analysis to find the most suitable treatment for each segment. We use predictive analytics to make accurate estimates of a consumer's propensity to repay, as well as the likely amount that the consumer will repay. Our unique solution also keeps eye on the reason of default and helps companies to incorporate that intelligence into their acquisition processes.