Machine learning
Solving final value problems with deep learning
Pricing vanilla and exotic options with a deep learning approach for PDEs
Setting boundaries for neural networks
Quants unveil new technique for controlling extrapolation by neural networks
Deep asymptotics
Introducing a new technique to control the behaviour of neural networks
Degree of influence: volatility shakes markets and quant finance
Volatility and machine learning were among the top research areas for quants this year
Machine learning will create new sales-bots – UBS’s Nuti
Technologists working to automate indications of interest from trading desks
HSBC exec: measure culture through smarter surveillance
Machine learning could help gauge positive sentiment from surveillance logs, says Elhedery
Model misfires raise questions over training data
Quants wrestle with how far into the past their machine learning models should peer
Regions deploys early-warning tool for credit risk
Risk USA: system alerted US superregional to impending defaults during Covid crisis
Machine learning hedge strategy with deep Gaussian process regression
An optimal hedging strategy for options in discrete time using a reinforcement learning technique
AML bill will swamp financial crime teams, banks warn
Proposed US legislation could force firms to run new and old systems in parallel, stretching resources
Danske quants discover speedier way to crunch XVAs
Differential machine learning produces results “thousands of times faster and with similar accuracy”
Alt data aims to shake up credit scoring business
Young firms, using machine learning methods to scrape consumer info, challenge established agency model
Banks welcome US overhaul of AML rules
Proposals signal shift to risk-based approach to financial crime detection
Differential machine learning: the shape of things to come
A derivative pricing approximation method using neural networks and AAD speeds up calculations
How Shell integrated FX algos into its corporate treasury mix
Interview: oil giant puts up to 50% of spot flows through algos, explains FX head Michael Dawson
Podcast: CFM’s Bouchaud on agent-based models and ESG investing
Hedge fund quant, and Risk.net’s new columnist, shares his unique take on markets
The data anonymiser
Non-parametric approaches anonymise datasets while reproducing their statistical properties
Podcast: Dario Villani on managing money with ML
Duality’s CEO discusses key to machine learning success, and the influence of Renaissance’s Jim Simons
Study suggests banks may be better off with simpler VAR models
Non-parametric VAR models perform well in calm markets, but miss the mark in volatile periods
Spotting co-movement breakdowns with neural networks
Autoencoders can detect changes in relationship between assets in real time