A fresh take on risk and valuation
We keep moving forward, opening
new doors and doing new things,
because we are curious, and curiosity keeps
leading us down new paths.
Behavioral Scorecard with Machine Learning Components

This article discusses the benefits of applying advanced analytics in the development of behavioural scoring models. It investigates how Machine Learning techniques can be used to model the behavioural scores of consumers in each step of the development and model assessment. Some concerns regarding the usage of Machine Learning in behavioural scoring models are addressed.

Implementation and Change Management Associated with Sophisticated Tools – A glimpse at QRM

This article unveils challenges of implementing changes on complex tools that use advanced databases. Based on the example of QRM Analytical Framework, it recommends a suitable change management process. Although this high level recommendations are based on Finalyse experience with QRM, the notions therein may apply to other sophisticated tools of similar nature.


This article analyses the effects of the COVID-19 from a bank’s credit risk point of view. First, it assesses how COVID-19 hurts the economy, the way the risk profiles of stock and potential clients deteriorate due to the pandemic’s negative effects on the economy, and it shows how this lowers credit supply. Then it elaborates on the regulations and policies – which basically target the amount of risk that banks can take on - aimed at preventing credit shortages and the results they had. Then, it explains the challenges that banks’ internal credit risk frameworks consequently face, and details valuable partners to help tackle them.

IFR/IFD - new prudential requirements for all investment firms

IFR and IFD have clearly been drafted in order to fil a gap in terms of prudential and governance regulation framework. The former situation presented some kinds of loophole between Credit Institutions that are subject to CRR / CRD IV, Investment funds that are subject to AIFM and UCITS (these regulations also provide a framework in terms of governance, risk management, remuneration, reporting and disclosure), and MIFID Investment Firms that were subject to none of them until now. The gap is now filled completely! The question I am sure all actors have in mind is how far EBA and ESMA are ready to go to consider the “implementation burden” for institutions! We might have a beginning of answer on the 4 September 2020!

Risk Appetite Framework and Decision Making

This article details the mechanisms governing risk decisions and the underlying complexity of using risk appetite as a component of the strategic decision.

COVID-19: Reactions of major regulators

This page will display the evolution of regulatory updates in Financial sector caused be the COVID-19 outbreak.

Sorrows of Credit Risk Model Validation

This article introduces the challenges of the ECB supervised entities regarding their internal validation of the IRB Approach. It also considers a benefit of use of Model Validation tool.

Implementing BCBS239, What does it take?

This article discusses how Finalyse carries out implementation of BCBS 239 projects. It shows the stumbling blogs that typically hinder implementation of such projects, such as big-bang approach or lack of communication between stakeholders. To avoid these pitfalls, Finalyse proposes a piecemeal, iterative approach which is discussed in further detail in this article. The article also provides several tips for translating a BCBS 239 plan into current systems.

Non-Maturity Deposit Modelling

This post demonstrates step-by-step a possible way to conduct Non-Maturity Deposit Modeling. It shows the practical challenges, taking as an example the overnight deposit rates in Hungary. In the current low-interest-rate environment, the modelling of non-maturity deposits has attracted interests from Banks. These models are used for critical purposes in banks such as the management of the interest rate risk of the balance sheet, or in their earnings, as it is now also expected from supervisory authorities. Finally, they are also used to determine a transfer price for deposits, to retribute the business lines in charge of collecting the deposits appropriately.

Machine Learning Model explainability –why is it important and methods to achieve it

Machine learning is today’s buzzword and it has gone through some phenomenal changes over the last few years. However, despite widespread adoption, machine learning models remain mostly black boxes. Hence it is essential to have techniques for explaining these black boxes in an interpretable manner. This article looks at the methods that are most used for interpreting machine learning models: SHAP, LIME and CP Profiles. It discusses advantages and drawbacks of each and shows how are they being used in practice.