Machine learning (ML) models have already been around for decades. The exponential growth in computing power and data availability, however, has resulted in many new opportunities for ML models. One possible application is to use them in financial institutions’ risk management. This article gives a brief introduction of ML models, followed by the most promising opportunities for using ML models in financial risk management.
The low interest rate environment has faced banks with structural changes in customer behavior and converging products such as savings and current accounts. ING, one of Europe’s largest players in the savings market and a long-term client of Zanders, has positioned itself as one of the frontrunners in this environment. We sat down with Tom Tschirner (head of market risk at ING Germany) and Maarten Hummel (financial risk officer at ING Group) to gather their view on modeling and balance sheet management after these structural shifts.
To respond to the concerns about the reliability and robustness of the IBOR benchmarks, the Financial Stability Board (FSB) recommended the development of an alternative (nearly) risk-free reference rate (RFR) in its report in July 2014.
Risk management and treasury specialists are using diverse models on a daily basis to manage various risks. It is easy to forget about the risk that is implied in using the model itself. What we refer to as ‘model risk’ can arise due to misuse of the model, incorrect model choices or inappropriate model use.
Benchmark interest rates are an essential part of financial markets. These interest rates are used for numerous financial products, such as bonds, loans and derivatives, and in the construction of discount curves. This has applications in fair value calculations, hedge strategies, sensitivity analysis, treasury and risk management systems, and much more.