When models fail
When models fail
Foreword
Preface
Acknowledgements
The evolution of models
The foundations of risk and uncertainty
Uncertainty: a taxonomy
Model risk and uncertainty: a survey of the institutional landscape
Model specification risk and uncertainty
Model operation risk and uncertainty
Data, models and their purpose
Artificial intelligence in finance: a synthesis of human and machine
A deeper dive into machine learning methods: their opportunities, limitations, risks and uncertainties
Measurement of risk and estimation of uncertainty in prediction models
Using models under risk and uncertainty
When models fail
Epilogue: models and the future
Failure happens all the time …. What makes you better is how you react to it.
Mia Hamm
12.1 INTRODUCTION
As Mia Hamm highlights in the epigraph above, although failure is a common experience, our response to it is what truly matters. She should know: she won two Olympic gold medals and two FIFA Women’s World Cup titles with the US women’s football (soccer) team. And every modeller knows it as well. In the period book-ended by the 2007–9 global financial crisis (GFC) and the 2020–23 Covid-19 pandemic, many financial models failed, but for differing reasons. The GFC failures of 2007/8 have a “we should have seen it coming” flavour, while the Covid-pandemic-related financial failures of 2020 may be classified as “we could not have seen this coming”. These are two distinct characterisations, perhaps with different lessons to be learned. The GFC is like a botched penalty kick due to a lack of sufficient preparation, whereas the financial effects of the Covid pandemic feel more like an accident while leaping for a header. The period between these two crises forms the basis of the story in this chapter: a story of failure, how we reacted and emerged (presumably) the better for it.
In the
Copyright Infopro Digital Limited. All rights reserved.
As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (point 2.4), printing is limited to a single copy.
If you would like to purchase additional rights please email info@risk.net
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (clause 2.4), an Authorised User may only make one copy of the materials for their own personal use. You must also comply with the restrictions in clause 2.5.
If you would like to purchase additional rights please email info@risk.net