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.
Getting ready for the Next Eu-wide Stress Test

On the 4th of November, the European Banking Authority (EBA) published the final package for the next EU-wide Stress Test, which will be officially launched in January 2023. This article outlines how the Stress Test exercise has changed, summarises the approach presented by the EBA Methodological Note for the next exercise’s run and discusses the future of stress testing.

Actuarial Data Science - Boost your model performance with Machine/Deep Learning

This article shows how machine learning techniques can boost model performance in terms of prediction accuracy and flexibility. These benefits may come with some setbacks: loss of interpretability (our next article will cover this topic) and additional hyperparameters to tune. To illustrate these different methods, we are going to use the French Motor Third-Part Liability dataset. This dataset contains risk features (such as exposure, power, vehicle age, driver age etc.), claim numbers and the corresponding claim amounts for the 413,169 MTPL policies over a one-year period.

Fundamental climate-related and environmental (C&E) risk considerations in the ICAAP

In this article we discuss the main C&E risk considerations to be made as part of the ICAAP, using the general ICAAP requirements as a starting point and combining them with the regulatory and supervisory expectations regarding C&E risk management.

Summary of TCFD progress report

Taking the 2022 Status Report published in October 2022 as a base for the analysis, this article discusses the current state of implementing TCFD (Task Force on Climate-Related Financial Disclosures) recommendations in the financial sector. We analyse why, despite some challenges, financial institutions should invest in developing methodologies for bridging the gap between the intended and realised shape of the TCFD reports.

EIOPA Application Guidance: Running Climate Change Materiality Assessment and Scenarios in the ORSA

EIOPA published the application guidance on running climate change materiality assessment and using climate change scenarios in the ORSA in August 2022 (“the guidance”). This is optional guidance which supplements EIOPA’s April 2021 Opinion on the supervision of climate change scenarios in ORSA (“the Opinion”). In this article, we discuss chapters 1 and 2, providing an overview of the guidance for the high-level reader.

Non-regulatory credit models – Retention and collection models

In this article we have presented the development of non-regulatory models and reasons why this work is important for risk related problems in financial industry. Those scorecards, even if they are not mandatory requested by the regulators, can significantly improve portfolio and cost control within the institutions. And although they are not directly connected with rating estimation/ECL calculation they can support risk estimation in many other ways.

A practical approach to predicting the IFRS9 Macroeconomic Forward-Looking PD

This article introduced a practical and end-to-end approach to model Point-in-Time PD in a manner that includes Forward-Looking Information for IFRS9 ECL calculation. Different techniques may produce results of varying accuracy depending on a specific dataset. The ‘best’ model should be selected by accessing different evaluation metrics and other aspects, e.g. related to model sensitivity.

Environmental Risks in the Microprudential Framework

Due to the unique features of environmental risks, extensive work is underway at the European and international levels to assess the extent to which they require urgent regulatory measures in addition to already existing frameworks. This article provides an overview of the microprudential framework’s most relevant shortcomings and their potential remediations. Its focus is on Pillar 1 aspects, addressing only the risk types most relevant from materiality viewpoint: credit, market and operational risks.

Machine learning for credit risk IRB models

This article examines the challenges and potential opportunities presented by machine learning when used to compute regulatory capital for credit risk using internal ratings-based (IRB) models. It also gives an overview of machine learning techniques that can be utilised for IRB modelling, as well as the results that can be expected.

2022 ECB Climate and Environmental risks agenda: preliminary indications

In recent years, the ECB has launched targeted actions to include climate and environmental risks in its ongoing supervision and has indicated addressing them in its list of priorities for 2022-2024. This article aims to go through the most relevant steps of the 2022 ECB supervisory C&E agenda and leverages on the results of the 2022 ECB climate stress test to provide preliminary commentary regarding banks’ preparedness for the existing and upcoming requirements.