In last week’s post, we discussed how data analytics is being used in debt collection and in particular, how a group from multinational computer technology group Oracle Corporation tested an analytical approach against a control group using traditional methods of collection. 

As we know from last week’s report, the traditional collections model uses a low-tech system to group customers into a few simple risk categories, based on simple analytics. Customer service teams are then assigned to follow up, with less experienced agents getting low-risk customers and more experienced agents getting high-risk customers. In this model, collections rely on human experience and intelligence to assess how best to achieve results for the bottom line. 

Worldwide management company McKinsey has been at the forefront of reporting on the use of data analytics in debt collection and reports one European bank automated 90 percent of communications with clients by developing two advanced-analytics models using machine-learning algorithms. By using models with around 800 variables – impossible for humans – the bank has realized more than 30 percent savings. 

Analytics-based solutions can assist with early self-cure.  By using many variables, banks can increase collector capacity by 5 to 10 percent, allowing agents to be reassigned to more complex collections cases.

Many banks use time in delinquency as the primary measure of default risk, but others are using analytics to build a risk model to determine value at risk. Leaders are moving to a future state in which models project conditional probability rather than assign customers single risk scores. The conditional score is dependent on a range of tailored approaches to customer contact and engagement; every borrower has several scores depending on the contact strategy and offer. This approach better calibrates the intensity of contact with each account. 

In another scenario, use of new analytics technology allows banks to ascertain a customer’s ability and willingness to pay and gauge whether the better path is a cure or an offer. Banks can resegment delinquent accounts to improve their decisions to offer early settlement, an approach that increases the uptake of offers while reducing charge-offs by 10 to 20 percent.

Models can predict the best offer, optimized for the needs of the bank and the customer. Banks can change the prompt, adjusting loan characteristics and offerings to those most likely to reduce charge-offs, including re-amortizing the term or changing the interest rate, consolidating loans, or settling. Making the right offer early, before accounts enter late-stage delinquency, can improve acceptance rates.

Finally,models will determine the accounts to retain in-house longer and he best third-party agency for each account that can’t be cured and tailor prices accordingly. 

The McKinsey graphic below shows how an analytical approach worked with two financial institutions. 


Lenders leading the analytics transformation are assembling data from many kinds of sources and developing different models to serve collections goals. The data sources include customer demographics, collections and account activity, and risk ratings. The most sophisticated lenders are creating “synthetic” variables from the raw data to further enrich their data. Machine learning helps identify markers for high-risk accounts from such variables as cash-flow status, ownership of banking products, collections history, and banking and investment balances. 

By using so many inputs from many different systems, lenders can dramatically improve model accuracy, lower charge-off losses, and increase recovered amounts.