The Data Analytics Blog

Our news and views relating to Data Analytics, Big Data, Machine Learning, and the world of Credit.

All Posts

Implement Collection Strategy Best Practice With Debtor Segmentation

February 15, 2018 at 10:08 AM

We have written a lot on ways to optimise your collection, but the simplest and most effective way is still to segment your debtors based on propensity to pay. Debtor segmentation is a best practice that every serious collections operation needs to utilise.

In this blog, we discuss what debtor segmentation is, what the effect of implementation will be and how to implement it as a solution in your collections environment.

What is debtor segmentation?

The best debt collection and recoveries operations deploy risk-based segmentation to identify a hybrid of high, medium and low propensity to roll and pay distressed borrowers to ensure that appropriate, tilted treatments are applied across the delinquent life cycle.

By analysing your debtors’ previous payment behaviour combined with credit bureau data, you will be able to identify which are high risk, medium risk or low risk. This segmentation into three basic categories gives you the opportunity to treat each debtor appropriately based on risk.

It is critically important to create and implement defined workout protocols that support rehabilitation and establishes an escalation trigger in early-stage collections. Ensure your collections and recovery strategy covers the ‘rehabilitation, repayment and recovery mantra’. Your process should be situational – based on the delinquency cycle and asset/product class. Rehabilitation endeavours should be explored and exhausted before the commencement of litigation. A fundamental requirement for consistent, accurate strategy execution is to deploy a tilted treatment framework across call scripts, short message services and any other engagement channel.

And this will lead to…?

Targeting your debtors with the right message and approach can pay off in various ways, such as better customer experience, increased payments collected, enhanced brand affinity, amplified brand loyalty and improved profits.

Sounds good! But how do I segment my debtors?

Several techniques can be used for debtor segmentation, from the simple k-means algorithm to the advanced model-based clustering to the continuously improving machine learning.

By using a method that includes machine learning, your models will continually update with new information provided and will teach itself if a debtor was identified as low-risk, but in fact, rolled on payment and how to determine such cases in future.

Whichever approach you take; the most important thing would be to ensure you have enough data to segment these debtors. Combining your historical payment and operational data, with credit bureau data, will enable you to get a more accurate picture of a debtor’s propensity to pay or roll.

Read more on our Genius Machine Learning as a Service offering if you are interested in implementing machine learning without the infrastructure cost to segment your debtors, or download our guide to optimising your collections and recoveries operation yield.

Increase your collection and recovery yields

Perry de Jager
Perry de Jager
Perry has been involved in Collections and Recoveries for the past 22 years, spending time in different market segments ranging from law firms to investment companies. At Principa, Perry has worked on extended projects within both South Africa and the Middle East with some of the largest financial organisation, providing on-site consulting within the collections and recoveries space covering strategy, process, people and technology.

Latest Posts

Solving the Credit Unaware Challenge with Psychometrics

At Principa, we engage with clients and organisations across the entire credit lifecycle and track the focus of the South African credit industry. For nearly ten years the focus has consistently been in the collection space, but recently (since early 2021) this has changed and a large number of our clients are focused on acquisitions and originations.

Predicting Customer Behaviour (PART 2)

In Part One of this two-part blog, we started providing a short overview of just some of the propensity models that Principa has developed. In this Part Two, we continue to look at different types of propensity models available across the customer engagement lifecycle that are used to predict behaviour and solve business problems. 

PART 2: How to Cure the Post Pandemic “Collections” Symptoms

In PART 1 of this two-part series, we explored how the current socio-economic climate resulting from the lingering financial hangover caused by the pandemic is negatively impacting the consumer's ability to settle a debt.