Synthetic data made with machine learning will struggle to capture the caprice of financial markets
Traditionally quants have learnt to pick data apart. Soon they might spend more time making it up
Few lenders favour Monte Carlo or parametric methodologies
Switch to historical simulation approach increases requirement by 71%
Pilot application to model enterprise risks cuts computation time from 10 years to 30 minutes
The SABR model for volatility is adapted to price risk-free rate caplets
Pricing vanilla and exotic options with a deep learning approach for PDEs
In this paper, the authors discuss all aspects of derivative pricing under the Heston–CLV model: calibration with an efficient Fourier method; a Monte Carlo simulation with second-order convergence; and accurate partial differential equation pricing…
The author assesses the quantitative effects of the recent proposal for more robust bank capital adequacy.
Fight for CDS market share heats up as Ice begins clearing options and LCH preps CDX offering
Use cases for new tech are piling up – from CVA to VAR. But so are the obstacles
Differential machine learning produces results “thousands of times faster and with similar accuracy”
ABN, ING and Rabobank working together; US quantum developer seeks patent for CCAR
A derivative pricing approximation method using neural networks and AAD speeds up calculations
Elliptical and Archimedean copula models: an application to the price estimation of portfolio credit derivatives
This paper explores the impact of elliptical and Archimedean copula models on the valuation of basket default swaps.
The heat potentials method is used to find the optimal profit-taking and stop-loss levels
In this study, the authors identify the three types of risks involved in an art-secured lending operation and present a framework to assess their combined effects via a Monte Carlo simulation.
In this work, we present a new Monte Carlo algorithm that is able to calculate the pathwise sensitivities for discontinuous payoff functions.
This paper proposes a new, flexible framework using Monte Carlo methods to price Parisian options not only with constant boundaries but also with general curved boundaries.
A generative neural network is proposed to create synthetic datasets that mantain the statistical properties of the original dataset
Interquartile distribution of VAR outputs highest for small banks, watchdog finds
Stephen Wilcox talks about getting pensions paid without the benefit of controlling ‘UK Plc’
A simulation-based model for optimal demand response load shifting: a case study for the Texas power market
This paper describes a case study of analyzing DR load-shifting strategies for a retail electric provider for the Texas (ERCOT) market using a Monte Carlo simulation with stochastic loads and settlement prices.
The authors propose a model for conduct risk losses, in which conduct risk losses are characterized by having a small number of extremely large losses (perhaps only one) with more numerous smaller losses.