The authors find that machine learning methods can generate satisfactorily performing credit score models based on data from the 90-days prior to the score date, where traditional models can perform poorly.
This paper presents a novel and direct approach to solving boundary- and final-value problems, corresponding to barrier options, using forward pathwise deep learning and forward–backward stochastic differential equations.
Removing arbitrage opportunities from simulated data used for training makes deep hedging more robust
Risk Awards 2022: Architect of deep hedging aims to supplant orthodox models with method based purely on data
Deep learning model can project prices around 100 ticks into the future
Research into valuation adjustments is back on quants’ to-do list
A multi-step path is forecast using deep learning and parallel computing
The P&L distribution of a complex derivatives portfolio is computed via deep learning
A novel NLP application built on a Google transformer model can help predict ratings transitions
This paper presents several algorithms based on machine learning to solve hedging problems in incomplete markets.
TCA methodologies that ignore partial fills “might be off by 20% to 30%”
News feeds are factored into models to predict credit events
Novel interpretability method could spur greater use of ReLU neural networks for credit scoring
Machine learning could help with loan decisions – but only if banks can explain how it works. And that’s not easy
Initial scepticism about using neural networks for derivatives pricing is giving way to enthusiasm
Intelligent robots can value complex derivatives in minutes rather than hours
Quants are using the theory of rough paths to distil the essence of financial datasets
Signatures can provide the synthetic data to train deep hedging strategies
Risk Awards 2021: new risk engine can run nearly a billion XVA calculations per second
Pricing vanilla and exotic options with a deep learning approach for PDEs
Quants unveil new technique for controlling extrapolation by neural networks
Volatility and machine learning were among the top research areas for quants this year
An optimal hedging strategy for options in discrete time using a reinforcement learning technique
ARR aims to anticipate volatility patterns to provide signals for risk management and trading