• Collection Strategies: Self-cure strategy and Data mining

    This article was last updated on (18/01/2023). Please note that the information contained in this article may have changed since the original publication date.

    Overview

    Financial institutions face the challenge of managing the growing numbers of delinquent customers while maintaining or cutting operational costs in the debt recovery process. To better understand the customers’ repayment behaviour, it would be ideal to group the customers based on their socio-economic status and financial obligations. The approach to grouping customers to their respective profiles could be done through the use of data mining and scoring techniques. We can segment the customers and design an adequate collection strategy for each segment effectively. Within the new business models, there is a need for more proactive and effective collection and recovery strategies, by utilising today’s flexible, responsive operational and IT systems to provide agility. Moreover, these strategies can facilitate the responses to new and emerging risks in the market and empower the organisation to deal with legacy risks inherited from earlier years.

    In the retail banking industry, the key success factors to improving debt collection effectively are through designing collection strategies that best fit the customer’s payment behaviour. The number of resources allocated for collection in any organisation is very limited, especially in retail banking, where the number of delinquent accounts far outnumbers the people in the collection team. In theory, a self-curing strategy is a strategy that provides a grace period for all customers to settle their outstanding balances without any direct action from the lender organisation. Identifying these groups of customers will help optimise the limited resources to collect from other customer groups or segments. Despite the method of collection, the value of collection is the same, therefore, to avoid preventable cost and customer irritation, the employed segmentation strategies must maximise the number of self-cure accounts. Moreover, the strategy should be able to identify the accounts that need more aggressive approaches to avoid escalations to higher delinquency levels.

    An Increase in Non-Performing Loans

    Due to the COVID-19 pandemic, countries around the world have seen an increase in non-performing loans (NPLs). Interestingly, it is reported that the economic growth of the East Asian Pacific (EAP) region has been decelerating even prior to the COVID-19 pandemic. High and increasing NPLs are telltale signs of weak economic conditions and poor health in some dimensions of the banking system. If left unaddressed, it can lead to negative effects on the banking system and economy. 

    Figure 1: NPL Ratios, GDP Growth, and Interest Rates in Asia, 1997-2019

    Source: Asia Regional Integration Center

    The figure above shows that within the time period as stipulated above, the changes in NPL ratios and GDP growth across different Asian regions are inversely correlated, while the change in NPL ratios and change in interest rates saw a direct correlation. Policy measures have been deployed by governments around the world to cushion the impact on the banking sector and their respective economies, due to concerns of NPL overhangs. 

    The rise in NPLs has made credit risk management an urgent issue. The huge impact of debt collection operations on organisations’ financial results is increasingly realised by corporations. Therefore, debt collection evolved into a profit driver, but the key is to collect wisely. Regardless of how a collection recovery is achieved, the value is the same. Hence, lenders need to know their customers better to be able to optimise their collection strategy and maximise the debt collected, while minimising the collection expenses and maintaining the customers’ relationship. Self-curing is a strategy that provides a grace period for a customer in which to pro-actively pay off their outstanding balance before investing the organisation’s resources to contact them to make a direct request for that payment.

    Segmenting the customers into different queues is a common practice for tailoring an appropriate collection strategy for each segment. As a general principle, the action for each segment could be differentiated into Type, Tone, and Timing. Moreover, the traditional collection process is divided into two areas i.e. early-stage and late-stage delinquents. The main objective in the early-stage group is rehabilitating the customers, while in the late-stage group, the focus is on recovering the balance as much as possible. In this insight, the focus of the article is on the early-stage delinquents and the timing aspect of the collection strategy.

    Self-Cure Strategy

    Theoretically, the self-cure strategy should be applied to all accounts, as long as they are sufficiently liable to make payments to offset the indirect costs of the self-cure strategy. These costs are usually incurred by the opportunity to collect payments via the next best strategy. In practice, high-risk customers will be treated differently.

    The expected benefit of a self-cure strategy is simply the expected number of payment agreements to be achieved as a percentage of all customers in the strategy – or the probability of payment. There is no direct cost associated with the self-cure strategy, therefore, the problem needs to be looked at differently, by studying indirect cost.

    The indirect costs of a self-cure strategy are derived from the fact that the probability of recovery declines as the time to make contact with the customer increases. The cost of a self-cure strategy is therefore based on the rate at which the probability of payment from the next best strategy shrinks. If a customer is expected to make a payment when they are called on the first day as opposed to being called on the fourth day, there is no cost attached to the self-cure strategy for those first three days. Therefore, regardless of the extent of the probability of payment from the self-cure strategy, no call should be made until day four. This is because, with no costs, any recovery made is value-generating and any recovery not made is value-neutral. However, if after the first three days, a customer who has not been contacted begins to become less likely to make a payment when eventually called, costs start to accrue. The customer should remain in the self-cure strategy up to the point where the probability of payment from the self-cure strategy is expected to drop to a level lower than the associated drop in the probability of payment from the next best strategy, as illustrated in Figure 2.

    self-cure, collection, payment

    Figure 2: Self-cure life cycle

    Strategies and Segmentation

    Most lenders have advanced to the concept that given the limited number of resources, low-risk customers can be left for a while to self-cure and high-risk customers should be contacted early. The collection strategies and actions must be chosen carefully to not alienate potentially profitable customers who might be going through a temporary stage of financial hardship. Targeting high-risk customers proactively makes sure that valuable low-risk customers have a chance to self-cure. By targeting accounts having the lowest probability of self-curing, the collection costs in early-stage delinquency can be radically reduced. Moreover, the lender may enjoy an increase in the level of customer satisfaction due to removing the collection treatment for the low-risk self-cure groups of customers.

    Economic conditions are one of the most important key factors which affect the strategy selection process. As economic conditions change, customer behaviour changes alongside it, therefore the collection strategy should change accordingly. The challenge is to be agile to reflect these changes. Employing behaviour and balance scoring will facilitate the identification of those who are most likely to self-cure. These scoring methods assist to predict the future performance of an account based on its past payment performance. These methods are popular and heavily used in pre-delinquency and early-stage delinquency. Combining score and balance provides the lenders with the ability to calculate ‘Balance at Risk’. Balance at Risk is the multiplication of behaviour score of good/bad odds with the current balance. It is a good measure to choose an adequate strategy and manage the limited resources wisely.

    risk, balance, behavioral scoring

    Figure 3: Combining outstanding balance and risk

    Although behavioural scoring and concepts such as Balance at Risk are utilised to determine the risk factor for each customer, there also exist other concerns as well. Data availability and quality of data are considered key ingredients for the success of any analysis. Traditional methods such as expert opinions and expert rule systems are not agile enough to cover the dynamics of collection. The introduction of data mining and machine learning to the collection domain empowers lenders to respond quickly to economic and behavioural changes. These methods constantly learn from historical data and discover new behavioural patterns as they emerge.

    Moreover, there are some well-known groups of customers with higher risk factors that require special treatments, which are explained further below:

    • Young accounts: Accounts less than six months old are considered risky due to a shortage of robust behavioural and payment historical data. These accounts are treated separately. Since there is not enough historical data to score these accounts, the bureau data, application score, and current account balance or amount due could be used to rank these accounts. It is proven that a phone call just before the first payment prevents many first-time delinquents and provides education about their responsibility and financial obligation. Moreover, early gentle reminders to those with moderate credit risk have also been shown to reduce the roll rate while still maintaining a positive relationship.
    • First-time delinquent: First-time delinquents are those accounts that miss their first payment. Failing to meet the first payment is a critical risk sign. Defaulting on the first payment on the one hand can indicate a potentially fraudulent account while on the other hand, it could reflect a lack of understanding about their responsibility and financial obligation. A similar but more comprehensive strategy should be adopted for these accounts.
    • Habitual delinquents: These accounts are for those that are frequently in and out of delinquency. These are the accounts that are aware of the collection methods employed by the organisation and are delicately weaving in and out of delinquency to their advantage. These accounts affect the Days Sales Outstanding (DSO) and cash flow. Therefore an appropriate strategy is needed to improve the DSO and cash flow for these accounts.
    • Broken promises: A promise to pay may be made by a customer during the rehabilitation process, i.e. phone conversation, or via letter. The promise is for the payment of an agreed amount and date in the near future. A broken promise is when the delinquent customer does not pay the agreed amount at the agreed point in time. Typically, a tolerance will be applied in respect of timing, i.e. one or two days, together with a tolerance set against the payment, i.e. payment of 95% of the agreed amount considered as full payment. Therefore, the number of broken promises can be utilised to determine the strategy.

    Data Mining and Behaviour Scoring

    Data mining as an approach to support computer-based decision-making borrow many algorithms from statistics, artificial intelligence and other fields. The thought of automatically extracting golden nuggets of knowledge from enormous databases, rather than the methods of data mining, can be a revelation.

    data mining, behavior scoring

    Figure 4: CRISP-DM data mining process

    Classification methods are the most commonly used data mining techniques that are applied in the domain of behaviour scoring to predict the risk level of customers. Statistical and machine learning methods, such as linear and logistic regression, decision trees, etc. have been used for developing behaviour-scoring models. Data mining is not just a set of mining algorithms, but rather a process. The process, as shown in Figure 4, aims at solving a definite problem or making a decision, by employing different mathematical and computational techniques to examine the related data stored in large databases. This is then followed by finding a solution based on the discovered patterns in data and applies the solution to the predefined problem. Data miners are fond of saying that data mining is as much art as it is science. What they mean by this statement is that the data mining process is a scientific endeavour overlain with a significant amount of artistic practice. The process is not an exact science but a combination of the familiarity in the subject matter of a particular domain and discovering the best possible methodology for achieving the desired goals.

    The probability that a customer will become delinquent during the predefined period of time will be estimated and the customers will be classified into different risk levels according to the estimated delinquent probabilities. This process is also known as risk assessment.

    There is a wide range of data mining algorithms and methods available and applied to behaviour scoring but not all of them are practical in the commercial environment. Since the Equal Credit Opportunity Act (ECOA) is widely accepted across the industry, selecting a method that could easily justify the reason behind the score that is calculated is critical.

    Data and Data Preparation

    Scoring systems utilise information relating to the traditional 5Cs of credit:

    • Character: The willingness to pay off debt.
    • Capacity: The financial ability to repay debt.
    • Capital and Collateral: Possessions or equities from which payment might be made.
    • Conditions: Reflecting the general economic environment, or special conditions applying to the borrower or the type of credit.

    For behaviour scoring, which predicts how the existing accounts will perform, the credit information that happened after the credit is granted should also be included. Extra information that is collected in behaviour scoring with regards to observation point A as shown in Figure 5 below. A predetermined period of time before the observation point is selected as a performance period, for instance, the previous 12 months, and then new variables that describe what happened in this period are added. ‘Outcome period’ is a period of time subsequent to the observation point A. The customer’s behaviour is assessed at the end of the ‘outcome period’, point B, and used as the dependent variable. The choice of time horizon is critical for behaviour scoring. The normal practice seems to be from six months to two years. Thus any shorter horizon would be insufficient to determine the rates of delinquency and it does not reflect the whole population. The time horizon of more than two years would leave the system to be susceptible to population drift in which the distribution of the characteristics of the population changes over time. Therefore, the population sample may significantly be different.

    data collection, performance period, outcome period

    Figure 5: Data collection time horizon

    Conclusion

    The benefits of adopting a self-cure strategy are self-evident. The reduction in the cost of collection, customer rehabilitation, increased customer satisfaction and many other direct and indirect benefits could be achieved by employing the appropriate strategy for each customer. In practice, achieving these benefits depends on the careful selection of the right strategy, the ability to access to right data, and analysing the data effectively to target the right customer.

    The use of analytics and data mining can make a significant distinction between the best-in-class and the average collection strategy. It is a matter of segregating different groups of customers within the population of delinquent customers and adopting the best strategy to optimise the collection effort for achieving the best collection result.

    JurisTech, your Preferred Partner

    Here at JurisTech, we pride ourselves in our solutions that power the economy. Introducing Juris Collect, an end-to-end debt collection system that meets your digital transformation needs. With the use of AI analytics and behaviour scoring, Juris Collect is capable of predicting self-curing accounts and potential NPLs. Coupled with Whiz, a debt collection strategy manager that automates your collection treatment activities and enables the comparison and deployment of multiple collection strategies, your revenue collection will come whizzing through your doors. Interested in finding out more? Contact us at contact@juristech.net today! 

    By | 2024-01-24T15:20:06+00:00 5th February, 2014|Insights|

    About the Author:

    The team at JurisTech's Marketing & Communications, a group of digital marketing strategists and content creators, delivers invaluable insights and expertise drawn from fintech experts across the entire JurisTech team. For media queries, get in touch at mac@juristech.net.