News & Insights Archives

Sinds 1 april 2021 zijn de leennormen van de Vereniging van Financieringsondernemingen in Nederland, kortweg VFN, voor consumptief krediet verder aangescherpt. Deze nieuwe leennormen zijn de uitkomst van afspraken tussen de VFN en de AFM. Hiermee wordt het krediet beter afgestemd op de persoonlijke situatie van de klant.

Daadwerkelijke kosten

Met de nieuwe leennormen moeten de, bij de VFN aangesloten kredietverstrekkers de financiële positie van hun klant nauwkeuriger bepalen. Het doel is het krediet nóg beter aan te laten sluiten op wat de klanten financieel kunnen dragen. In de leennormen moeten bijvoorbeeld de daadwerkelijke kosten van kinderopvang, een auto of de woonlasten worden vastgesteld.

Betrouwbare data

Dit betekent dat verstrekkers meer gegevens moeten verzamelen, vastleggen en moeten meenemen in de berekening van de leencapaciteit. Voor veel kredietverstrekkers, die nog geen of een gedeeltelijk geautomatiseerd proces hebben, zal dit neerkomen op een verhoging van de operationele kosten. Ook wordt het proces minder efficiënt. Los hiervan is de vraag hoe betrouwbaar de verschafte data is.

Kleinere kredieten

Voor mensen die geld willen lenen, zullen de nieuwe regels mogelijk extra barrières opwerpen. Het gaat er hierbij niet eens zozeer om dat er mogelijk een lager bedrag geleend kan worden. Dat is tenslotte een uitvloeisel van de zorgplicht en in het belang van de klant. Wél is het zo dat de verhoogde operationele kosten het waarschijnlijk niet meer rendabel maken om kleinere kredieten te verstrekken!

Meer lenen

Een gevolg van het ontbreken van kleinere kredieten is dat de kans groter wordt dat mensen meer zullen gaan lenen dan ze nodig hebben en oorspronkelijk van plan waren. Een ander bijkomend feit van de nieuwe regels is, is dat het voor klanten niet altijd even makkelijk is om deze benodigde gegevens te verzamelen en aan te leveren. Weet jij bijvoorbeeld direct waar je huurovereenkomst ligt? Of kun je gemakkelijk bij je salarisstroken en deze uploaden als je vanaf je mobiel krediet wilt regelen?

PSD2 data

Met de verscherpte leennormen zijn geautomatiseerde cloud-oplossingen en -processen van kredietverstrekkers dan ook nog relevanter geworden. Alle gegevens die nodig zijn en moeten worden opgevraagd voor deze processen, kunnen tegenwoordig betrouwbaar en met één druk op de knop worden verzameld. Alleen een PSD2 toestemming van de klant is hiervoor nodig. Deze data kan worden verwerkt in een rapport en ook direct worden gebruikt in de verdere operationele processen van de kredietverstrekker. Een behoorlijke efficiënte tool dus.

Betere klantervaring

Wil jij als kredietverstrekker grip houden op de operationele kosten, kleinere kredieten blijven aanbieden en toch een betere klantervaring bieden? RiskQuest helpt je hier graag bij. Wij zijn specialist in kwantitatieve krediet-risico-modellen en actief voor de top van de financiële wereld. Wij bieden geautomatiseerde cloud oplossingen, én hebben de inkomsten- en lastentoets op basis van de nieuwe leennormen al geïmplementeerd!

Wil je hier meer over weten of wil je een keer een demo-versie zien? Stuur dan vrijblijvend een korte e-mail naar Tabor.Smeets@RiskQuest.com of bel 06-23611491!

As AI solutions grow more capable, they play an increasingly important role in decision making—which raises well-known concerns that models might not be fair. A credit-card-fraud detector might be biased when it intervenes and blocks transactions; loan applicants might be rejected after transaction profiling. In the Netherlands, discrimination and unfairness are considered such serious affairs that Rutte’s third-term government resigned over the unfair treatment of those in need of social tax support (Toeslagenaffaire, early 2021). Could similar misery arise between the bank and their exit clients, when they assemble and figure out none of them are Dutch? Find out how we can ensure you are making the right choices.

Fortunately, just like the model’s accuracy can be measured, so can its bias. However, there are several challenges:

free choice in the definition of fairness,
the “is”/”ought” problem (predictions versus truth),
correcting bias,
balancing different interests, and
using sensitive data.

Our previous blog about Discrimination and Free Will discussed the fine line between behaviour that’s a free choice and behaviour that’s related to group characteristics. This blog considers free choice from a different perspective: how do we determine what is fair?

Sidenote: Article 1 of Dutch constitution

All persons in the Netherlands shall be treated equally in equal circumstances. Discrimination on the grounds of religion, belief, political opinion, race or sex or on any other grounds whatsoever shall not be permitted.

Anti-discrimination laws are clearly written, but clearly not by data scientists. Let’s phrase fairness in the context of a binary decision: you either get a “yes”, or you don’t. Algorithmic fairness is the field of data science that gives us the perspectives to quantify fairness. Unfortunately, there are multiple ‘definitions’ of fairness, and they are mutually incompatible. In other words, there’s a choice to be made. Here are three options (loosely based on the guidelines from the UK authority ICO):

Demographic parity: decisions should be representative of the population.

- The distribution of people that gets a “yes” should look just like the distribution of all people. So, within statistical error, just as many males as females should get a “yes”.

Error parity: decisions should be fair towards those that deserve it.

- Does everyone who should get “yes” have an equal chance of getting it? Are we not holding out on males or females that ought to get a “yes”?

Equal calibration: decisions should be correct, fairly for everyone.

- For everyone that did get a “yes”, did they ought to, with equal chance? Are we not giving males or females more “yes”es than we ought to?

As the great philosopher Kant wrote, ethics are laws by which to exercise free choice. In this case, we look for principles to base off our definition of fairness. If the question is: “Which fairness definition should we consider?”, the answer could be: “All of them!”—which drives us into compatibility issues. As we will see, to truly make the fair call, we’ll want to shift focus from statistical results to their broader impact.

Broadening our understanding, the “is”/”ought” problem is terminology also hijacked from ethical philosophy (where it means something else). In this case, we mean that the decision that “is” is not the decision it “ought” to be. Example: a bank account holder is exited due to a false suspicion of fraud. The problem: we may not even know what the decision “ought” to be. In fraud cases, we can sometimes use existing analysis outcomes as the ground truth. Those outcomes “ought” to be—now we can analyse the fairness of model decisions against this ground truth to calculate error parity and equal calibration.

But if we don’t have such labels, we don’t know what “ought” to be, and we can only calculate demographic parity for bias quantification. Asking our algorithm to output the population distribution is a very strong requirement, however, which we may not intend. Maybe, in some way, males “ought” to get a “yes” more often than females. For instance, while we roughly have as much males as females, public data shows that males are four times more often convicted of money laundering than females.

While this statistic raises concerns of its own, accepting it for a moment as our reality, we expect our transaction monitoring system to also trigger more often on males than on females—not because they are males, of course, but because risky transactions are apparently more often executed by males. If the TM system’s distribution is in between the population 50/50 and the CBS 20/80, we have no reason to suspect unfair treatment.

However, what if our bias quantification shows unfair treatment under one of the above definitions? This may not be a problem if the impact of an unfair decision is negligible—but sometimes, it will be problematic. Under a standard optimisation approach like maximum likelihood, we expect optimal model performance, but this may amplify existing bias in your data. It may also negatively influence humans interacting with the algorithmic decision. Technical solutions are to re-train your model under constrained optimisation, or to add a penalty term for any disparity. This will be specific to the model you’re optimising and hence may impact your modelling approach from the start. (Contact us to discuss details.)

Inevitably, imposing fairness on an unfair model leads to performance reduction—which could be costly. Data science can quantify the difference and provide solution options. However, a true assessment of what’s fair should consider all parties involved. For instance:

clients and prospects (i.e. involving your Legal and Privacy offices),
management levels and their personal responsibility,
operational cost to the bank (e.g. your Operations department),
risks of reputational damage (i.e. ORM), and
societal impact and the role of the government.

Working with all involved, the data scientist can clarify the impacts of each option. But the final decision might call for management to strike a balance between ethical goals, costs, and responsibility. It’s here that we see that ethics is really about our choices.

The impact of unfairness depends a lot on the situation. An example with strong interventions are some U.S. universities on the policy that freshman distribution should resemble population distribution to some degree (demographic parity). Seeing how universities prepare a new generation for important societal positions, this seems a way to try and balance out society itself. It may not be the bank’s role to intervene like that—but should the bank just accept for a fact that money launderers are more often male than female?

(But alas, then we also won’t find out if females are actually just much better at laundering money.)

Conclusion

Our conclusions can be summed up as follows.

‘Being fair’ is a conscious effort. It can call for nontrivial choices, especially if your use case is already susceptible to bias.
Hence, we view fairness as a balance struck very deliberately. Your choices here don’t exist in a vacuum; they impact your business and society.
We use algorithmic fairness to guide understanding—but there is not one fairness algorithm to rule them all. The final call requires you to have a holistic understanding of all perspectives.
We involve the right decision makers and stakeholders to make that final call.

When it really matters, data science is a necessary, but not sufficient element to base your decisions off of. That’s why we’re both modeler and consultant.

Sidenote: GDPR special category data

It’s only fair to include the European GDPR in our consideration, as it’s protecting our pricavy w.r.t. the sensitive data that we usually think about in context of discrimination. However, the GDPR currently also presents a problem for fairness, since it’s very strict about processing special category data, such as religion, even for purposes of bias quantification. The UK authority ICO has taken the position that bias quantification serves “substantial public interest” and hence falls under GDPR exemption, meaning UK data scientists can process such sensitive data strictly for this purpose. In the Netherlands, the AP (Authoriteit Persoonsgegevens) has not clarified this issue yet, meaning NL data scientist could potentially break privacy law if they use special category data even for bias quantification. The best we can do in the current situation is a maximum effort, i.e. doing as much as we can to mitigate unfairness, then weighing the residual discrimination risks against the positive impact of our model.

For more information on this topic contact Hans Heintz (Partner) or Sven de Man (Partner)

If you want to join our RiskQuest team, please check our current job openings here

The climate all around the globe is changing. Although this is a gradual process, some of the consequences are already visible in the world today. Also in the Netherlands more extreme weather conditions could be observed over the past years.

The negative consequences of climate change are recognized and are translated in plans for change. These plans have resulted in the Paris climate agreement in 2015. Overarching goal of this agreement is to limit the increase in the average earth’s temperature to 2 degrees Celsius until 2100. Studies have shown that without action the temperature is expected to increase by 3-4 degrees Celsius.

Both the climate change as well the actions required to limit climate change impose risks for financial institutions. In order to outline these risks RiskQuest has set up a series of three blogs related to this topic. In this first part, the specific climate risks for Dutch banks will be outlined. The second blog provides an overview of the current status of climate risk management at banks, with a main focus on the Netherlands. In the third blog we will provide our vision on how banks should incorporate climate risk in their business.

Types of climate risk

Within climate risk a distinction should be made between physical risks and transition risks.

Physical risks consist of natural phenomena such as drought, extremely high or low temperatures, perspiration, storms and flooding. Such events can result in damages to premises and products, thus resulting in losses. As not all of these risks are covered by insurances, part of the losses are borne by the households, businesses and/or the government. This will also have an impact on the exposure which banks have to these parties, e.g. in the form of mortgages, corporate loans and stocks/bonds.

Thus far, banks have often excluded such physical risks from their financial analyses, as those risks are perceived to be very uncertain. There is, however, sufficient proof that the climate is changing and although the timing of extreme events is uncertain, its effects are likely much more predictable than forecasts of the financial market which currently are included in their analyses.

Transition risks on the other hand focus on the risks borne by financial institutions in relation to changing policies, rules and regulations which aim to limit climate change. Most of the increases in temperature are caused by greenhouse gas emissions. In order to limit these emissions, measures are taken, which will be felt the hardest by sectors with high emissions such as fossil fuel producers, energy and transport sectors, the built sector, heavy industry and agriculture, but also individual households will be impacted.

Physical climate risks

One of the major physical climate risks in the Netherlands which is generally not covered by insurances is flooding. Ever since the North Sea flood (Watersnoodramp) in 1953, protecting the Netherlands from high water, has been a top priority for the Dutch government. The sufficiency of the dikes is investigated regularly and if required actions are taken. However, future rises of the sea level are uncertain. Within the Netherlands 60% of the land is susceptible to flooding, so although the likelihood of a flooding is limited, it can have significant consequences.

Most eminent risks of flooding for financial institutions are:

Damages of premises and products of clients, impacting the (credit quality of) exposures which financial institutions have within the flooded area.
Damages of their own premises, impacting their operations.
A large flooding can impact the perceived credit quality of the Netherlands, resulting in a downgrade of Dutch sovereign bonds.
There could be secondary effects from a flooding such as lower economic growth in future years and political instability.

The assets on the balance sheet of the major Dutch banks are not limited to exposures within the Netherlands. However, in their report Waterproof, the Dutch Central Bank (DNB) has investigated the exposure towards countries with higher physical climate risks and it has concluded that this exposure is limited.

Estimating the impact of a flooding for a bank and its exposures and subsequently the amount of capital it should reserve is not a straightforward process. It concerns situations which have not happened before and the amount of available data to make such estimations is therefore limited. In its report DNB therefore advises to perform scenario analysis in order to make an estimation of the impact. Furthermore banks should analyze their geographical concentrations in order to test their vulnerability towards such an event.

Transitional risks

Reducing climate change requires actions to be taken. Largest impact on the climate comes from greenhouse gas emissions, so especially sectors which depend on this, such as fossil fuel producers, the energy, transportation and agricultural sectors, will need to change.

For banks this could have an impact on the value of exposures towards companies in these sectors and countries which depend to a large extent on these sectors. Such risks could materialize in the form of lower profitability, resulting in lower stock prices, but also downgrades in their bonds and the credit ratings of their loans.

How quickly such sectors change depends on government policy, technological developments and consumer behavior. Abrupt changes might have a bigger impact as more gradual changes provide sectors with time to prepare.

DNB has investigated that on average 11% of the balance sheet of Dutch banks concerns exposures towards carbon intensive and fossil fuel sectors, see figure 1 below. It is therefore important for banks to keep track of (required) climate change reducing measures within these sectors and even support and facilitate them. The latter is possible by providing favorable financing for such measures and issuing and purchasing green bonds.

It is noted that most of the exposure towards carbon intensive and fossil fuel sectors concerns products with a maturity of less than 5 years giving banks the opportunity to act timely.

The numbers is figure 1 below concern an average over the banking industry in the Netherlands. Individual banks should investigate their specific exposure towards carbon intensive sectors.

Figure 1: overview of exposures to carbon intensive sectors (Source: DNB)

Dutch banks also have a significant exposure towards real estate. This concerns both retail and commercial property finance. Tightened regulation in this sector to reduce greenhouse gas emissions, e.g. in requirements related to energy labels should therefore also closely be monitored.

If sustainability investments in real estate have to be financed by the owner of the real estate, this could impact their ability to repay the loan they have with their bank. Banks should therefore gain insight in the current energy labels of the real estate serving as collateral to their loans.

Figure 2: overview of label distribution commercial real estate of banks in the Netherlands (source: DNB)

DNB has investigated that currently 46% of the collateral of commercial real estate of Dutch banks, for which the energy label is known, has an energy label of D or worse, see figure 2. For office buildings at least a level C energy label is required as of 2023.

Actions are therefore required, which for banks should start with identifying, quantifying and monitoring these specific transition risks within their portfolio. Next, banks should mitigate their transition risks by starting to finance sustainable solutions and by excluding clients in sectors which are harming the climate goals.

Measure, monitor and manage climate risks

The previous sections provided an overview of the climate risks for banks. Being able to make proper estimates of these (potential) risks can bring competitive advantages to banks; it will allow the banks to steer on the existing risks, but also to incorporate it in their pricing strategy and to develop new products which support reaching its climate related goals.

As it takes time to execute these measures, e.g. it takes time to build a mortgage portfolio with the desired average energy label, it is import to start timely. Next to direct financial benefits, contribution towards reduction in climate change can also result from banks’ internal ethical compass and it can improve its reputation.

But also regulatory requirements (SFDR) force banks to report on ESG measures, with additional requirements for products that support sustainable objectives. The goal of these requirements is twofold. It provides a more transparent comparison between companies and ensures that products which are marketed to be sustainable are actually sustainable. As of 2022 banks are required to disclose these items in their financial statements. Also the Task Force on Climate Related Financial Disclosures) recommendations (TCFD) has issued guidelines on reporting on climate risks, which many Dutch financial institutions intend to follow.

Also with the deadline of these regulatory requirements approaching, banks have already started to address these risks and to develop a strategy on how to limit these risks and to contribute to reaching the goals of the Paris climate agreement.

In our next blog on this topic, we will provide an overview of what various banks currently already do on this topic. We envision that banks can improve their climate risk management. Partly this will be the consequence of more data and more information of future legislation becoming available. But more improvements are possible, by not only considering climate risk on a standalone basis, but by integrating it directly into other risk models, such as credit risk models and pricing models. Our vision on the future of climate risk within financial institutions will be provided in our third blog on this topic.

For more information on this topic contact Vincent Schothuis (Manager), Johannes Lont (Manager) or Diederik Hemmes (Senior Consultant)

If you want to join our RiskQuest team, please check our current job openings here

Discussing the ambiguous article and showing the impact of the maximum recovery period

During intensified regulatory oversight, ECB found that banks could keep defaults with high losses open forever which kept many high losses out of the modelling dataset, leading to seemingly low losses in the portfolio. To prevent this, the latest AIRB models ought to be developed including a maximum recovery period: a certain period after which the bank is not allowed to estimate any recoveries for the purpose of modeling. Having these cases open for a long time now leads to having high loss cases in the dataset.

In our opinion, this is a debatable piece of regulation, especially for collateralized asset classes like residential mortgages. The article in the regulation can be interpreted in at least two ways and the additional Q&A text from EBA has not provided a definite answer on the implementation. Without question, the impact on LGD is very large.

First we will introduce the maximum recovery period and discuss the options for interpretation. Then, we assess the impact and finally address some argument for the discussion of interpretation, including a view from the regulator.

MRP Explained

For the modeling process of AIRB LGD models, banks should take into account all defaulted exposures in the dataset[1] . A part of the data will consist of unresolved cases, for which realized loss is currently unknown. Sometimes open default cases have been in default for a very long time and it is questioned whether there will be any recoveries at all. To address this problem and avoid cases are kept open on purpose, the EBA introduced the maximum recovery period[2] (MRP) for banks. The MRP is defined as:

´A period that reflects the expected period of time observed on the closed recovery processes during which the institution realises the vast majority of the recoveries´.[3]

For the purpose of modeling[4], observed losses for unresolved recovery processes should be adjusted for the maximum recovery period. How losses for open defaults should be adjusted is split into two types of open cases based on the current time-in-default:

Type 1) For cases that have passed the MRP at the moment of modelling no recoveries should be estimated[5]:

Type 2) For cases that have not yet passed the MRP at the moment of modeling the rules below should be taken into account for constructing an observed loss:

Two interpretations of the article on the MRP

Article 158 of the guidelines in which the MRP is explained states that:

a) they should take into account all observed costs and recoveries;

b) they may estimate future costs and recoveries, both those stemming from the realisation of the existing collaterals and those to be realised without the use of collaterals within the maximum period of the recovery processes.

We think that the interpretation of the second statement (art. 158b ) is open for some debate. Let us discuss two different interpretations below on how to construct observed losses for unresolved cases.

Interpretation 1:

They may estimate future costs and recoveries, both

those stemming from the realisation of the existing collaterals

and

those to be realised without the use of collaterals

within the maximum period of the recovery processes.

Here both recoveries from collateral and other recoveries (so all recoveries) should only be estimated up to the MRP (conservative interpretation)

Interpretation 2:

those stemming from the realisation of the existing collaterals

and

those to be realised without the use of collaterals within the maximum period of the recovery processes.

Here it is allowed to make an estimation for recoveries from the collateral, even after the MRP (progressive interpretation)

Reading both statements, which one do you thinks is more plausible? We think that the right, progressive, interpretation is more sensible for this piece of regulation for various reasons, which will be discussed in a later paragraph.

Impact

First, we want to look at the large impact the interpretation has on the LGD of an average Dutch mortgage portfolio.

The difference in LGD predictions stems from the (LRA) calibration where unresolved cases are included. Depending on the length of the modeling dataset and the moment of modeling, up to 20% of the data can have an unresolved status. If the moment of modeling is during a crisis with many defaults, this percentage could be even higher.

Part of these open cases will be of type 1, as previously defined. These cases should write off all open exposures, i.e. no estimation of future recoveries is allowed. Typically, the vast majority of a mortgage loan is recovered by selling the collateral at the end of the default. Therefore, the fact that the case is still open must mean that the collateral is not yet sold. And as the collateral is not sold yet, the open default will have an observed LGD of approximately 100%. This is visualized in the figure below.

The relative size of type 1 cases will depend on the MRP. A long MRP will lead to fewer type 1 observations and more type 2 observations. Type 1 observations will have the same observed loss under both interpretations, but due to their high (constructed) loss will have a large impact on the observed LGD. The unresolved type 1 cases and their observed costs and recoveries are illustrated in the figure below.

The remainder are type 2, where the time-in-default has not yet passed the MRP. Looking at the figure below, the conservative interpretation leads only to an estimation for the orange recoveries. The progressive interpretation also allows estimation of the green box, representing recoveries from collateral.

As the chance of exceeding the MRP increase as the time-in-default increases, we observe in the figure below that the difference in observed LGD diverges for the different interpretations. This figure shows the average observed LGD, where the LGD for open cases is constructed without MRP (blue), with the conservative interpretation (orange) and with the progressive interpretation (green). By taking the average of these LGD values per time-in-default months, we can clearly see a time-in-default relation introduced by the MRP, which was not clearly present before.

Irrespective of the interpretation, conforming to the MRP rule drastically increases the observed LGD and thus RWA, for a mortgage portfolio. The progressive interpretation will lead to a lot smaller increase, displayed in the table below.

Why we prefer the progressive interpretation

In our view, it is not likely that a collateral becomes worthless after a certain artificial time period. Is it really sensible, for a mortgage, to deem the collateral worthless after the MRP? If there exists a house that can be sold by the bank, it feels overly conservative to assume that no recovery from collateral is made.

The Bank for International Settlements (BIS) stresses to have a small gap between the regulatory EL amount and the provisions required under Expected Credit Loss accounting approaches. However, as the regulatory EL includes the MRP it will be significantly higher than the accounting ECL. The progressive interpretation will lead to a smaller gap.

Concerning choosing an MRP length, the EBA states the following:

‘CAs should ensure that the concept of the maximum length of the recovery process is not misused and that the lengths specified by institutions are not excessively long for a specific type of exposures.’

It is likely that banks will choose an extremely long MRP in order to reduce the impact of the MRP on RWA. EBA recognizes this and explicitly mentions that misuse should be avoided. The progressive interpretation will lead to similar impact with a more reasonable choice for the MRP.

A regulators point of view

Although we believe that the progressive interpretation of Article 158 is more sensible from an economic and modelling point of view, we observe that the current market practice is to follow the conservative interpretation. Indeed, as pointed out above, to limit capital impact banks are incentivized to choose a long MRP. Our current understanding is that the regulator’s perspective is also to follow the conservative interpretation, overlooking the consequences such as models that are hard to align with risk management intuition and regulatory issues such as ELBE and stage 3 provisions becoming non-comparable.

Conclusion

One way or another, including the MRP will have a large impact on the LGD of a mortgage model, which is overly conservative in our opinion. The interpretation of the regulation also comes with a large impact. Effectively writing off fully collateralized loans in the model dataset makes our modeling minds nervous. We think that banks are in need of an explicit guideline on this topic from the regulator and that the regulator needs to rethink the treatment of unresolved cases and MRP specifically for collateralized loans such as mortgages.

For more information on this topic contact Victor van Dongen (Consultant), Janneke van Schijndel (Senior Manager) or Sven de Man (Partner)

If you want to join our RiskQuest team, please check our current job openings here

[1] Guidelines on PD estimation, LGD estimation and the treatment of defaulted exposures– article 149

[2] Guidelines on PD estimation, LGD estimation and the treatment of defaulted exposures– article 158(b)

[3] Guidelines on PD estimation, LGD estimation and the treatment of defaulted exposures– article 156

[4] Specifically referring to the long run average calibration for LGD

[5] Guidelines on PD estimation, LGD estimation and the treatment of defaulted exposures– article 157

Imagine creating a model that reviews thousands of transactions every second and aims to flag the transactions related to money laundering. This is something that has become possible thanks to advances in artificial intelligence in recent years, and even appears to be a necessity for banks that are flooded with huge amounts of daily transactions. Hence the challenge of fighting money laundering is growing and RiskQuest is thrilled to be able to help the banks in the process of designing and creating Anti-Money Laundering (AML) models.

During the fight against money laundering other financial crimes like financing of terrorism, fraudulent transactions and corruption can also be captured. Even better, banks can decide to not only monitor money laundering but to also actively fight other financial crime. New models may be designed each aimed to detect a different specific fraudulent behavior. Examples are counter human trafficking, illegal wild life, corona fraud or healthcare fraud. In this blog the latter will serve as an example on how to develop such a transaction monitoring model and thus fight financial crime!

Healthcare fraud in the Netherlands

Before creating a model to fight a specific form of financial crime there must be sufficient reason to believe that this behavior occurs often and that this behavior could be captured by transactional data. Let’s tackle the first subject and dive into the health expenditures landscape of the Netherlands.

In 2015 the healthcare system of the Netherlands was decentralized, meaning that the responsibility of certain government duties were shifted from the government towards municipalities. Municipalities are among other things responsible for work and income, youth, long-term sick and elderly care. This decentralization was the starting signal for an increase in fraudulent health care declarations, often through healthcare providers (‘zorgbureaus’). These ‘providers’ for instance receive insurance money from home care declarations which is never provided, or they cheat with personal budget (PGB), the so-called PGB-fraud. Unfortunately the patient is often victimized, since they do not receive the care they are entitled to. However, sometimes the (fake) patient is engaged in the fraud as well.

Since the decentralization, it is fairly easy to become a healthcare provider nowadays; one does not need a diploma or patients to register. Subsequently it is very difficult for the municipalities to check whether everything is correct and non-fraudulent. Some even say that fraud is risk-free for such a healthcare provider at the moment and there is no sanction.

In the meantime, the Public Prosecutor (‘Openbaar Ministerie’ (OM)) estimates that hundreds of millions of Euros per year are used for fraud with healthcare funds. Partly because organized crime focuses on this ‘field’. The government and insurers are gradually seeing valuable healthcare funds disappear towards sports cars and hotel stays in Ibiza. This leak of hundreds of millions of Euros each year should be fixed!

Investigative journalists from Follow The Money (FTM) thought it was time for action. They built a model that checked annual financial statements of health care providers and filtered out those companies with high margins. Margins above 10% and high dividend payments were found to be indicators of fraud.

However, while developing our own tool RiskNavigator we found that using annual financial statements for analyses of a client is time-consuming, old fashioned and not up to date. Besides, it appears that annual financial statements are sensitive to fraud, which is a big problem in the healthcare fraud scenario. On the contrary, client transactions do not lie. Hence creating a model based on client transactions is more accurate and less fraud sensitive.

Reason enough to start making a transaction monitoring model, but how?

Time for some (model) action

When creating a transaction monitoring model, one should first decide on the scope of the clients. In the case of the healthcare fraud detection model one could for instance decide on only including those accounts that are registered under a certain SBI code, or maybe including those accounts that receive funding from insurance companies. If you stay focused on the behavior you would like to capture, a good prior selection may achieve a better performing model.

The second step in creating a transaction based model is finding the right data. Not only transactional data, but also client or company information, network information and other enrichments may be useful. Now is also the time to find your label (or target) information, in the case of the healthcare fraud detection model try to gather all historically known fraud cases.

Once you gathered all the useable sources it is time to create our data pipeline. In the data pipeline we combine all the input sources and create understandable features that our model can train on. Regarding the healthcare fraud detection model, good features to start with are for instance margins and dividend features, since FTM already found those are good risk indicators. Since the quantity of transactional data can be immense, one could also consider aggregation of transactions. Consider aggregating transactions for each client. This can for instance be a daily, weekly, monthly, quarterly or yearly aggregation.

Make sure to create your data pipeline in a structural way, such that development and production environment both can make use of the same underlying library. Git tooling is a DevOps add-on that may be convenient during development of the data pipeline. It allows the data pipeline to have multiple versions and allows contributors to work together on the same project. Even one step further is to train the final model on the production environment, such that no alignment test needs to be done between production and development environment.

Once you have your features, you need to combine them with historic label information and decide whether sufficient labels are available to perform supervised machine learning or that we should aim at unsupervised machine learning techniques. Sometimes explainable non-machine learning models or even clever business rules may be preferred to capture certain behavior. It may also be preferred to use a combination of techniques (an ensemble). This part of the project requires a lot of testing, for instance testing different features, different models, different hyperparameters and different scopes. To make a considered choice of the final model one can use MLflow. This tooling may be convenient during development, since it helps to register all findings and performance of tested models, but also during production, since it helps with registry of the model and automatic deployment.

After choosing a final model, one could also determine whether automatic retraining is preferred each time the model is executed. When new labels are available why not use them as soon as possible?

Detecting healthcare fraud

During model development analysts are often available to give feedback on the model performance. In the case of creating a healthcare fraud detection model one could try to retrieve specific feedback on the chosen client scope or certain features used in the model. Precious information is for instance behavior that analysts never find risky, or behavior that is always risky.

But we need to give something back to the analysts. Using machine learning techniques comes with a price. As previously discussed in the blog ‘What can Credit Risk modelling learn from Counter Financial Crime (Models) and vice versa?’ , the models themselves are somewhat of a ‘black box’. Hence we should make sure that our models and outcomes are understandable and explainable for analysts.

Documentation is a big part of this and spreading the word is as well: explaining how the models work, showing the performance of the models and provide insight in the use of models. Another important aspect is training the analyst in order to correctly interpret model alerts. Feature importance or transaction importance per alert may be a big help for the analyst.

Another thing that can’t be forgotten is bias quantification, for more information on this topic please read our previous blog ‘Are you mindful of discrimination in (your) models?’ and wait for our upcoming blog on Algorithmic Fairness.

Once we checked the performance of the healthcare fraud detection model, and made sure our outcomes are understandable and non-discriminating it is time to put the model into production. Let’s find those fraudsters!

Conclusion

In this blog we aimed to inform you on how to develop a transaction monitoring model. This blog used the example of the healthcare fraud detection model, however many other transaction models can follow this setup. At RiskQuest we have gained experience in creating models that fight financial crime and are fully aware of the importance of widespread knowledge sharing within an organization. We are open to share our knowledge and support you on the challenges you face in this area. Let us fight financial crime together!

For more information on this topic contact Emma Immink (Consultant), or Sven de Man (Partner)

If you want to join our RiskQuest team, please check our current job openings here

Counter Financial Crime (CFC) modelling is a relatively new field which has seen a lot of rapid progression in the past years. This rapid progression has been spurred on by the Dutch Central Bank (DNB) after it became clear that banks were insufficiently deterring and detecting financial crime, which resulted in severe fines from DNB. Banks have made a great effort to implement various ways of countering financial crime, most notably in anti-money laundering but also in terrorism financing and fraud. Advanced modelling techniques are used as creative methods to find any criminal activity.

Large progression in credit risk modelling has also been made. One of the main reasons for this progression is the introduction of many new regulatory standards concerning credit risk models published by the European Banking Authority (EBA), leading to updated requirements and methodologies. Focus of these new regulatory standards is on the robustness of required data, definitions and models. These have led to a need to update all credit risk models.

Both types of models differ significantly from each other in terms of purpose, but the challenges faced are similar. At RiskQuest, we have experience in both types of models. In the remainder of this blog, the lessons learned from credit risk models will be applied to Counter Financial Crime models and vice versa.

Machine learning methods

Counter financial crime models make use of advanced machine learning techniques with the goal to detect irregular or suspicious behavior that could indicate money laundering, whereas the industry standard in Credit Risk Modelling is the use of Ordinary Least Squares (OLS) regression and Logistic regression. The main benefit of the methods used in credit risk modelling is that the relationship between the dependent and the independent variables is very clear and can be shown with a single equation. Instead of these more traditional methods, machine learning techniques can be used for credit risk models. In general, these techniques can be used to achieve higher model performance on a chosen metric, since they can capture a greater variety of relationships using the same datapoints.

Unfortunately, there are two major downsides to the application of machine learning techniques for Credit Risk Modelling. The first downside is that it is questionable that machine learning models meet all regulatory requirements set and reviewed by EBA, ECB and AFM. This is related to the second downside, which is inherent to the use of machine learning techniques, is that machine learning models are often thought to be opaque in terms of their exact operation. While the model inputs and output are clearly defined, the models themselves are a ‘black box’.

This problem, however, does not just apply to credit risk modelling but is present for all uses of machine learning models. Hence, machine learning has seen significant progress in the development of explainability tools. These tools attempt to identify the relevant risk drivers as inferred by the machine learning models. The relevant risk drivers are those risk drivers that had the biggest impact on the model score. With these tools the relationship between the model score and the most relevant risk drivers becomes clearer. Counter Financial Crime modelers have used these tools to help analysts understand the models and how their output was generated.

The output of the machine learning models is used by analysts to determine whether the alerted behavior proves to be suspicious. In order for the analysts to fully understand why specific behavior is flagged, they need to understand how the model output is generated. These efforts to improve the understandability are very effective in reducing the operational costs and time spent on these alerts.

Similar techniques could also be used in credit risk modelling. One could apply these machine learning methods to a credit risk modelling problem and attempt to extract the most important relationships from this model. This relationship could then be recreated using Ordinary Least Squares regression or Logistic regression. This approach allows for full explainability of the model, with the added benefit that more complex relationships can be discovered through machine learning techniques. Additionally, machine learning methods can also be used to deploy a challenger model. This challenger model can be used to assess if the traditional credit risk models can still be improved, as well as provide a performance benchmark.

Use of transactional data

Transactional data plays a key role in the identification of money laundering, since cash flows reflect the behavior of the client. These cash flows can lead to a trigger of suspicious behavior. In credit risk models, most explanatory variables are related to behavior of the client with respect to delinquency and utilization of limits, or their financial statements. While delinquency and utilization information is mostly up-to-date, financial statements can be outdated, especially in crisis periods, where previous financial statements are not a good representation of current financial strength. This is where transactional data can be used to improve models.

Transactional data can be used to enrich credit risk models. The biggest advantage is that transactional data can be updated near-instantly and be reflected in the credit risk model scores. Furthermore, transactional data also contains information on debts, fixed expenses and provides insight in other cashflows that could be used as Significant Increased in Credit Risk (SICR) triggers, such as missed tax payments and interactions with debt collection agencies. Additionally, transactional data is of very high quality and highly standardized, making it ideal for incorporation in a credit risk model. The availability of transactional data, however, is limited to the accounts that are available to the creditor. Since large companies often have numerous accounts with several different institutions, transactional data should always be used in combination with a companies’ overall cashflows for a complete overview.

What can counter financial crime learn from credit risk?

While the counter financial crime sector is making great strides in terms of innovation and the use of sophisticated techniques, the model governance still has a lot of catching up to do. Although models in Counter Financial Crime have to go through numerous steps of model validation and other types of stakeholder approval, this entire process has not been refined yet. This is not a surprise, since CFC is a relatively new field and has a lot of freedom to introduce models and needs to find creative ways to detect a range of different kinds of financial crime. A natural consequence of this environment is that the model governance is constantly challenged to adapt to these new modelling approaches.

Despite the successful efforts to develop explainability tools for machine learning models, there are still challenges in the model governance process. Model validation often lacks a framework for the validation process for these kinds of models. As a result, the validation is a long process involving lots of communication back and forth with the model developers. This means a lot of operational time and money is wasted, which could be spent better if the process was more streamlined. These challenges are not only limited to model validation.

Requirements from DNB demand each of the bank’s business lines to cover and mitigate their own risks. From an organizational perspective, these business lines are rather detached from the modelers who build the machine learning models, not to mention the gap in knowledge. As modelers are continually developing and releasing new versions of their models, there are implications for the risk mitigation efforts of each individual business line. They are stakeholders of the models but are often not involved in the development process or not fully aware of the model specifics. This can result in a lot of unnecessary pushback and inefficiency. Creating an environment of successful cooperation is beneficial to the developers as well, since modelers will always need business knowledge to optimally counter financial crime.

Fortunately, within banks, there is already a field with a long history in model governance and stakeholder management. A field where each step of the process is guided by an extensive set of standards: credit risk. Credit risk is heavily regulated and for each step of the model governance process there is a clear set of predefined standards. Having a similar set of frameworks would be very beneficial for the counter financial crime department and increase its efficiency. Even though it is important that CFC keeps its innovative spirit and not be restricted too much, the knowledge and experience from the credit risk domain would still be transferrable and prove to be valuable for the model governance.

Conclusion

Although counter financial crime and credit risk are two fields that serve vastly different purposes, the challenges they face are similar. As the two fields excel in different aspects, it could be very beneficial to instigate more cooperation between the service lines. This will lead to increased knowledge sharing and improved model performance. Credit risk can learn from CFC to use machine learning techniques and apply transactional data in their models, while CFC can benefit from the extensive knowledge of credit risk experts in the model governance domain.

At RiskQuest we have gained experience in both fields and are fully aware of the importance of widespread knowledge sharing within an organization. We are open to share our knowledge and support you on the challenges you face in this area.

For more information on this topic contact Sjoerd Keijsers (Consultant), Mark Croes (Consultant) or Sven de Man (Partner)

If you want to join our RiskQuest team, please check our current job openings here

In recent years, new regulations with respect to credit risk models were published at a fast pace. Consistency between data sources, definitions and model methodologies were important topics for a number of guidelines from the regulators. This led to an intensified relation between the models for the two most important fields of application with respect to credit risk models: RWA calculation and provisioning.

Many banks decided to develop AIRB and IFRS9 models combined. Currently, the market seems to evolve into developing one probability of default (PD) base ranking model that will be calibrated differently for AIRB (through the cycle, TTC) and IFRS9 (point in time, PIT) purposes. Banks that decided to make two separate models for these purposes had a hard time to explain their choice to the regulator.

One could argue that a low-risk client under AIRB will probably be a low-risk client under IFRS9 as well. Therefore, multiple ranking models, with, likely, different ranking outcomes would lead to counterintuitive results. However, is the combination of the development of both models as straightforward as it seems?

This blog will focus on one specific inconsistency between the AIRB and IFRS9 requirements that led to challenges during our latest model development and many sleepless nights for me personally.

On the one hand we have the development of the IFRS9 multi-year PD model. The model is required to estimate the lifetime PD of the loan given the current and future state of the macroeconomy. This is a complex requirement, especially given limited data history. Therefore, it is market practice to calculate one-year PIT migration matrices and multiply them to obtain the multi-year PIT PD. However, the matrices should be Markov in order to achieve correct multi-year horizon estimates. The Markov property implies, in this context, that the probabilities of a set of possible rating migrations only depends on the current rating and is therefore independent on the full rating migration history.

On the other hand, there is the heterogeneity requirement for pooling of the AIRB models. This means that all pools should have a significantly different observed PD. However, the significant difference will be tested on the AIRB horizon, which is one year. This mismatch in horizon is exactly where the shoe pinches. Two facilities with the same one-year PD could have a different multi-year PD. However, due to the requirement of heterogeneity they will be merged into one pool, which leads to non-Markov properties of the migration matrix. This non-Markov behavior leads to problems in the development of the IFRS9 model.

The description of the inconsistency can be illustrated by the following example. Assume the following start population and the (true) migration matrix:

Note that this is in line with reality where most of the clients are healthy and have a low PD. Note that these numbers have been chosen to minimize the period of convergence of the observed default frequency (ODF), see the figure below:

With this start population we can calculate the number of defaults that we will observe over a five years period. In the first year 19 defaults will be observed. The distribution of the facilities over the ratings can be calculated in the same way. In year 2, rounded to an integer, 20 defaults will be observed and in years 3-5 every year 18 defaults will be observed (also rounded to an integer). In total we observe 93 defaults over the first five years. This number can also be obtained by multiplying the migration matrix 5 times with itself:

The expected number of defaults in five years is calculated as: 1000 × 0.071+120 × 0.134 + 60 × 0.103 = 93(rounded). Note that this three-state process is observed and will be estimated if all information is available.

However, the one-year default probability of rating 2 and rating 3 are equal. Therefore, based on the heterogeneity requirement from AIRB, these ratings will be merged into one rating. This leads to the following matrix (given the start population of rating 1, rating 2, rating 3 and default [1000,120,60,0]):

If we look at the number of estimated defaults in the first and the second year, we see an exact match with the three-state matrix (both estimated and observed). However, from the third year onwards, the number of estimated default for the two-state matrix is higher. After 5 years we estimate 99 defaults, instead of 93. Therefore, merging these two states leads to non-Markov behavior.

It is interesting to see that a one state model would be Markov, due to the chosen equilibrium population. Note that this would not be the case in real life, because there would be no equilibrium. However, usually the default probabilities are linked to the macroeconomy. Therefore, the one state model can be used for multi-year PD, without failing the Markov test. Note that a ranking model, with only one rating would be Markov, but would not meet any other requierements and is therefore not a solution.

Note that the example seems odd, but in practice these types of state traveling happen a lot. For example if there are separate ratings for facilities that currently have arrears, facilities that had arrears in the past 12 months and clients that did not have arrears in the past 12 months. In reality the observations are a combination of all kinds of patterns.

Preferably, as a modeler I would like to have:

The same ranking model for both AIRB and IFRS9
Heterogenic buckets under AIRB requirements
Pass the Markov test on the migration matrix for IFRS9

From the example, it can be concluded that it is impossible to fulfill all three requirements. Therefore, we have to choose two. In our vision it depends on the specific situation at the client what would be the best choice. It is market practice to go for 1 and 2 and apply scaling to compensate for non-Markov matrices. This could be a good approach given that multi-year IFRS9 is only used for stage 2 facilities. Furthermore, the majority of the ECL will be based on the risk in the first years where the deviation is small and we are able to improve by scaling. However, if the bank uses the IFRS9 models also for extensive stress testing then not only the default probability is relevant, but also the performing-to-performing migrations, the bank might want to choose another strategy.

We as RiskQuest are always open to discuss the best strategy for your bank.

For more information on this topic contact Janneke van Schijndel (Manager) or Sven de Man (Partner)

If you want to join our RiskQuest team, please check our current job openings here

RiskNavigator powered by PSD2 (RiskQuest & Invers)

What is RiskNavigator?

RiskNavigator is a risk management solution that enables credit issuers to efficiently and effectively assess loan applicants
It provides credit issuers with a complete credit risk management dashboard based on real-time banking transactional data powered by PSD2
It is an integrated end-to-end solution that can be adopted instantly

What can RiskNavigator do for you?

We bring credit issuers and customers together. RiskNavigator delivers an integrated and customized credit risk management dashboard (e.g. customer credit-profile) by using enriched banking transactional data powered by PSD2 (supplied by Invers, a FinTech enabler with a PSD2 license). The tool operates in the following four key steps:

Retrieve all banking transactional data once customers grant RiskNavigator access to their personal and / or company-specific financial transaction history
Enrich banking transactions with predefined classifications and categories
Profile customer credit status (e.g. key metrics, lending capacity and early warning signals)
Prepare extensive financial analysis in a user-friendly risk management dashboard that is ready-to-use

Why should you use RiskNavigator ?

RiskNavigator is developed by RiskQuest, a consultancy firm that specializes in risk management solutions in the financial services industry and has extensive knowledge in the credit risk domain.

RiskNavigator is a cloud based ready-to-use solution that can be adopted instantly
RiskNavigator helps credit issuers not only to speed up credit approval processes but also to gain deeper and more meaningful insights into the customer’s credit status in a user-friendly and intuitive risk management dashboard
RiskNavigator’s dashboard provides detailed credit insights such as repayment capacity, lending capacity, debt-servicing capacity, early warning signals and in due course the credit risk score. These credit insights are all based on customer’s banking transactional data
RiskNavigator’s dashboard will enhance and complement the existing traditional risk assessment based on annual report and its respective financial ratios
RiskNavigator provides ongoing and real-time risk monitoring functionality via early warning signals. It enables the credit issuers to monitor and update their credit assessments in real time for current loans

Who are RiskQuest and Invers?

RiskQuest (developer of RiskNavigator)

RiskQuest is a consultancy firm in the Netherlands that specializes risk management solutions in the financial service industry. RiskQuest has over 15 years of extensive knowledge in credit risk models and credit assessments that help the financial institutions to develop its risk strategy, define suitable risk appetite and its respective credit solutions. Risk models and machine learning algorithms developed by RiskQuest have helped financial institutions gain a deeper and more meaningful understanding of their key risk factors that are embedded in the business portfolios. This provides the financial institutions with guidance for decision making.

Invers (provider of the enriched PSD2 transaction data)

Invers has 25 years of experience in customer insights in the field of financial situation of the individual consumers and SMEs. Invers is specialized in customer insights by analyzing cash flows patterns of individual consumers and SMEs through three core areas: 1) retrieving bank transactions, 2) enriching banking transactions with predefined categories, 3) creating descriptive financial analyses of individual consumers and SMEs. These analyses are used by banks, lenders, financial service providers, e-commerce and software suppliers. They integrate Invers’s web services via API’s with their own services for its respective daily operations, client servicing and financial institutions’ financial analysis.

RiskNavigator contact details

Hans Heintz
RiskQuest B.V.
Herengracht 495
1017 BT Amsterdam
info@RiskQuest.com
Office number: +31 20 693 29 48
Mobile number: +31 6 81 50 90 88

In 2009, the Swedish Central Bank (SCB) introduced negative interest rates for the first time in history (Christophe Madaschi, 2017). The European Central Bank (ECB) followed in 2014 and introduced negative interest rates to boost the economy during the aftermath of the global economic crisis. Since changes in interest rates affect a bank’s profitability, it is of utmost importance to have well performing interest rate models. However, not all interest rate models are able to deal with negative interest rates. In this blog, we stress the importance of good interest rate models, review various candidate models and provide solutions in case traditional models do no longer function with negative interest rates.

Negative interest rates

The idea behind the introduction of negative interest rates was twofold. First, a negative interest rate stimulates economic consumption, since consumers will be less inclined to save money. Secondly, funding for companies becomes cheaper and therefore more attractive, and will stimulate economic production. Combined, these two effects should lead to an economic growth stimulus.

Importance of appropriate interest rate models

For all banks, but in particular for banks with a lot of retail deposits, interest rate models are needed that can deal with a negative interest rate policy (NIRP). Banks with such models can create a competitive advantage because appropriate interest rate models contribute to sound risk management, and also because they are able to better adapt their business to changes in the interest rate environment.

The importance of appropriate interest rate models is also recognized by regulators. In July 2018, EBA guidelines on IRRBB (EBA/GL/2018/02) were finalized as part of Pillar II of Basel’s capital framework. These guidelines discuss Interest Rate Risk in the Banking Book (IRRBB), i.e. the risk that adverse movements in interest rates affect the earnings and the economic value of an institution. The guidelines state that in low interest rate environments, institutions should also consider negative interest rate scenarios. Therefore, it is not only the competitive advantage aspect, but also the regulatory requirements that stress the need for interest rate models that can deal with a NIRP.

It is important that the interest rate models are aligned with its purpose. For the IRRBB, different interest rate models are needed than for example the trading book. For the trading book it might be preferred to use a more complex interest rate model in order to accurately capture the volatility smile. The drawback of these complex models is that more simulations are needed to compute the present value of derivatives. When institutions hedge on a frequent basis, the question arises whether these complex models are the most convenient. A less accurate model, which is easier to use, can be preferred in this situation.

What interest rate models are commonly used and what are their limitations in a negative interest rate environment?

To forecast interest rates, in practice often short-rate models are used. Short-rate models are mathematical models that model the future evolution of the short-rate over time. However, in the current negative interest rate environment, some of these models lose their functionality or their predictive power. The specifications of these models can for example be restricted to allowing only positive current short-rates or assume a log-normal distribution for the interest rates, which results in a lower bounded interest rate of 0%. These model characteristics prevent the interest rate models to predict negative interest rates in a negative interest rate environment. However, some of these restrictions can be circumvented, as we will discuss.

One of the short-rate models that has problems with modelling the evolution of interest rates in a negative interest rate environment, is the Cox-Ingersoll-Ross (CIR) model. The CIR model uses the square root of the current short rate as input to forecast interest rates. Although imaginary interest rates sound like an interesting concept, practically speaking the square root of negative short rates is not defined.

The horizon for which short-rate models provide accurate predictions, can be relatively short. Therefore, for predictions on longer horizons, other types of interest rate models might be preferred. An often preferred model is the LIBOR Market Model[1], which models a set of forward rates for different periods that are directly observable in the market. A downside of the LIBOR Market Model is that it assumes that the forward rates are log-normally distributed. The log-normal distribution restricts the forecasted interest rates to be positive, resulting in the fact that negative interest rates can’t be predicted by this model.

What adjustments can be made to the models to make them suitable under a NIRP?

Some interest rate models, such as the LIBOR Market Model and the Cox-Ingersoll-Ross (CIR) model, are not able to forecast negative interest rates. For these interest rate models, the model specification needs to be adjusted before they can be used to properly model the interest rate movements in a negative interest rate environment.

The non-negativity limitation of the LIBOR Market Model can be solved by introducing a shift in the log-normal distribution, which allows for negative interest rates. For the CIR model an additional parameter can be added to the model specification to ensure that the current short-term interest rate is shifted to a positive value, such that the square-root transformation is defined (Orlando, Mininni & Bufalo, 2019).

A potential drawback of this adjustment for the LIBOR Market Model is that, since the log-normal distribution is shifted, the distribution is still capped by a negative boundary. How to implement the shift also introduces expert judgement and possibly frequent recalibrations in a declining interest rate environment. This also is a drawback for this adjustment related to the CIR model, since the shift must be large enough to ensure that the current short rate becomes positive and in a declining interest rate environment this shift needs to be constantly larger.

What model alternatives are better equipped to deal with a NIRP?

A popular choice in the current low interest rate environment is to use shadow rate term structure models. These models use a shadow short rate rather than the actual short rate . The actual short rate is defined as:

that is, the short rate equals the shadow rate, if this is above the lower bound , while the actual short rate remains at the bound if the shadow rate is below the bound. In order to account for negative interest rates, the lower bound can be set to a negative time-dependent value. Shadow rate models can capture the decline in yield volatility far better than a popular benchmark model that ignores the presence of a lower bound. (Lemke & Vladu, 2017).

Other popular choices are regime switching interest rate models. By means of regime switching techniques, different models are used depending on the environment at hand: negative, low, normal or high interest rates. This has the advantage of always using a suitable model, whatever the level of the interest rate may be. A drawback of regime switching models is that the model increases in terms of complexity. Traditional short rate models are easier to interpret and are often arbitrage free and provide closed form formulas. The increase in complexity of the regime switching interest rate models makes it more difficult to calibrate the model on the market data.

Conclusion

The NIRP affects the profitability of a bank, and therefore suitable IR models are needed that can deal with this situation. Not only is this desired from a competitive advantage perspective, but it is also a regulatory requirement. While some models are still valid, other models need adjustments either by changing their specification, or combining models into one model using regime switching techniques.

At RiskQuest, we are well aware of the effects of the NIRP, both on banks and on interest rate models. We are also mindful of the importance to align the complexity of the model with its purpose, where complexity should be balanced with frequency of use. We are ready to advise and provide the best possible IR models for each situation and tailor this for specific needs.

For more information about IRRBB, negative interest rates or specific interest rate models, please contact Lino Kragtwijk (consultant) or Nick Verbaas (consultant)

If you want to join our RiskQuest team, please check our current job openings here

[1] Note that the LIBOR Market Model can also be used to model other interest rates than the LIBOR