The Data Analytics Blog

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

All Posts

Solving the Credit Unaware Challenge with Psychometrics

July 23, 2021 at 12:02 PM

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.

New lenders, including a few new banks are entering the market and whilst they all scramble for their share of the market, the question on how the credit unaware segment should be targeted, crops up.

The credit unaware segment comprises those consumers who have yet to take up a credit product and hence have no credit record. As such they have no rich credit score, making a credit decision on them very difficult. It is believed that the credit unaware segment in South Africa consists roughly of about 18 million consumers. That’s a large number of potential customers!

So how does one assess a customer where very little data is available? You create new data! Enter psychometrics and the psychological profiling of the consumer. Apart from determining an employee’s fit in a particular organisation, did you know psychometrics can help predict leadership, autism and even your political affiliation? So why not also your attitude towards repaying debt? If you think about it, how do we best determine whether someone is going to repay a debt? We look at whether he/she has done it before and we base our judgment on payment history. To use a medical analogy, we look at the symptoms of someone’s attitude or circumstance, rather than the cause.

Psychometrics is different in that it allows us to assess the root cause. Put differently, psychometrics can assess our motives, in other words, whatever motivates and drives our everyday decisions.

The great thing about the psychometric score, unlike a dynamic credit score, is that it is fairly static as it predominately measures traits that don’t really change. Research suggests that motives and personality traits remain stable, even across diverse life events. This means that we can determine a customer’s psychometric score and use it a year later, if required.

So how does it all work?

Some may recall that the market dabbled with psychometrics more than ten years ago. The tests however, were word-heavy and retrofitted from employment applications. Also, there were measurement issues with bias and faking/gaming.

Principa has now teamed up with Astra Constantine to offer a new approach to psychometrics for credit assessment. Astra Constantine’s Dynamic Risk Assessment© uses a situational judgemental test (SJT), designed by industrial psychologists which measures a variety of factors, including:

  • Decisiveness
  • Decision making
  • Values
  • Traits
  • Emotions

This is all done through an easy-to-understand 10 question quiz where candidates choose the two situations that best describe how they feel about a given topic. They drag those icons to the spaces on the right. Each question puts the candidate in a variety of situations - sometimes positive, sometimes negative - and measures the candidate’s responses. There is limited opportunity for gaming and bias, literacy challenges are significantly reduced and characters used are generally gender/race/age neutral. The completion rate is 95% and the median completion time is between 5 to 7 minutes.

Psychomtrics - Astra Constantine-1

(Trade Mark - Astra Constantine)

 

The outcome of the test is measured as a risk score representing a customer’s propensity to repay a loan or facility.

Risk Profiler - Explainer Infographic

In a previous blog we listed some answers to frequently asked questions about Dynamic Risk Assessment©.

 

Deploying psychometrics within your credit strategy

 

Cellphone screen with graphic for personal preference profiler

The deployment of the Risk Profiler© tool is a relatively straightforward process. For digital originations processes, applications will be captured after which a credit bureau check is done. If the customer is credit unaware, that customer can be asked to complete a psychometric assessment. This is accessed via a link on the digital originations system. When the test has been completed, a score is produced and sent back to the loans origination system. Cut-offs can be set. Similarly, applicants who are credit aware but have a score near the cut-off (medium scores), could be asked to complete a psychometric test with cut-offs set. This is illustrated in the diagram below.

 

Digital origination process flow diagram

Opportunities for psychometrics

Psychometric scoring has been deployed in a number of lending organisations for the risk assessment of both consumers and small and medium enterprises. Whilst the credit unaware segment offers the most promise, the test can be used in conjunction with bureau scores for credit aware and could be used when the credit score is in the middle to high range near the cut-offs.

There are also other non-bureau credit scoring solutions out there. The specific advantages of psychometrics are that it is established, easy to install, scores are relatively static and it may be a tool for the economically immobile to finally get access to credit.

To find out more about how psychometric testing could help your business, get in touch with us.

 

Thomas Maydon
Thomas Maydon
Thomas Maydon is the Head of Credit Solutions at Principa. With over 17 years of experience in the Southern African, West African and Middle Eastern retail credit markets, Tom has primarily been involved in consulting, analytics, credit bureau and predictive modelling services. He has experience in all aspects of the credit life cycle (in multiple industries) including intelligent prospecting, originations, strategy simulation, affordability analysis, behavioural modelling, pricing analysis, collections processes, and provisions (including Basel II) and profitability calculations.

Latest Posts

Principa Partners with Astra Constantine to Deliver Psychometric Solutions to Credit Grantors

Customers Can Predict Outcomes by Adding the Power of Psychometrics to Credit Determination

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.