Modelling
A statistical technique to enhance application scorecard monitoring
Application scoring plays a critical role in determining the future quality of a lender’s book. It is therefore important to monitor the performance of an application scorecard to ensure it performs as expected.
Libor replacement: a modelling framework for in-arrears term rates
Andrei Lyashenko and Fabio Mercurio expand rates modelling to the post-Libor world
Getting risk models runway ready
Banks struggling with internal model requirements may soon opt for off-the-rack rather than bespoke
Cleaning noisy data ‘almost 70%’ of machine learning labour
Quants flag signal-to-noise ratio as key to reducing overfitting risk
Machine learning governance
The ability of machine learning models to read great quantities of unstructured data, spot patterns and translate it into actionable information is driving a significant uptake in the technology. David Asermely, SAS MRM global lead, highlights the need…
New applications in Asia’s financial crime analytics
Financial crime is a fast-growing problem for Asia‑Pacific financial services firms. Working with outmoded systems and patched-up processes to detect, monitor and eliminate potential threats, banks are spending millions on sophisticated new solutions to…
Danske Bank hires Alexandre Antonov
Risk’s 2016 quant of the year to join Danish firm from Standard Chartered
BoE makes climate risk a hot topic for banks
Financial institutions must entrust oversight of climate risk to named individual under senior managers regime
Volatility scaling unravels as market patterns shift
Waning power of quant approach could be a reason for trend following’s malaise
Systematic manager puts up guardrails for AI
Boston-based Acadian aims to limit risks from complex, machine learning algorithms
Fund houses get picky over where to use machine learning
Buy-siders limit usage of deep learning techniques due to haziness over their inner workings
EU’s model study finds problems with bank VAR methods
Banks surveyed by the ECB had an average of 32 issues with their market risk models
All along the watchtower – Surveillance tools against market abuse
Surveillance tools against market abuse are enjoying a technological revolution in analytics, while anxious supervisors are also closing in on market practices. Risk.net hosted a webinar in association with NICE Actimize to analyse the threats and…
Making technology count in a C/ETRM world
As businesses grow, so does their need for modern, agile and cost-effective commodity/energy trading risk management (C/ETRM) solutions. Pioneer Solutions explores how its next-generation, highly configurable C/ETRM systems take advantage of the latest…
Converging on sound model risk management practices
Although most banks are progressing rapidly towards a certain standard in MRM practices, the rate of progress is uneven and so are the ambition levels. Management Solutions provides a summarised overview of the state of MRM evolution and how banks are…
Modelling cyber losses could get easier – study
Cyber losses behaved much like non-cyber losses when grouped by severity, so perhaps less data is needed