Latest Insights

What can banks do to address the challenges posed by rising interest rates?

Markets have been confronted with a sharp increase in interest rates over the last months, resulting in a material change in level and steepness of the yield curve. Today’s interest rates are positive, the yield curve relatively flat and, in some currencies, even (slightly) inverse. The rise in interest rates poses a significant challenge for banks. This challenge involves managing the impact that rising rates have on the bank’s IRRBB key risk metrics as well as new EBA regulation related to supervisory outlier tests (SOTs) for IRRBB.

Machine Learning Workshop

With the trend towards increasing computational resources and larger datasets, the application of machine learning (ML) in finance has gained attraction. Financial Institutions are interested in how and where ML models can be of added value in their business model.

On the move for an Operational Resilience Framework

Currently, for many organizations, operational resilience is at the top of the agenda of the Board and senior management. The COVID-19 pandemic clearly showed how vulnerable societies and organizations can be to unexpected and unforeseen events.

News Sentiment Analysis and Credit Risk

Do we still need humans to monitor and interpret qualitative data for our risk models?

Recent technological advances increase the possibility of using qualitative data in risk models to ensure a timelier recognition of threats. News articles, which can be seen as a type of unstructured data, are flooding the world every day. However, one can imagine the time it would take to manually process all this information. Recent developments in natural language processing (NLP) show some very promising results in automating that task by a computer. We assess the possibilities of these recent advances within credit risk management.

Can machine learning predict the probabilities of default?

According to Moore’s law, computing power doubles up each two years. This performance increase in computing power makes machine learning increasingly efficient each year, and widely applicable. But does this also apply to credit risk issues?