We propose a novel approach to the anonymisation of datasets through non-parametric learning of the underlying multivariate distribution of dataset features and generation of the new synthetic samples from the learned distribution. The main objective is to ensure equal (or better) performance of...

MVA is becoming a dominant XVA component in interdealer derivatives trading in the post Margin Reform environment. Unlike FVA which can be either a funding cost or a funding benefit, MVA due to BCBS IOSCO IM is always a cost because of non-rehypothecability of the initial margin posted under the...

This paper discusses the implications of having risk management systems built on simplified methodologies. As an example, quanto adjustments for risk factors simulation are considered. The impact on counterparty exposure and regulatory capital calculations is quantified

This paper discusses a class of methodological issues that frequently arise in the risk management systems such as PFE and CVA engines. Simplified methodology and shortcuts come at a price, sometimes a steep one. To account for model deficiencies and disconnect between the calibration and the...

Our objective is to learn the natural curve shapes with the help of Artificial Neural Networks (ANN). Our research aims to improve curve dynamics generated by the parametric models and the PCA. By running the ANN on the dataset of historically observed term structures of forward commodity prices...

The presentation slides cover two promising machine learning applications of parameterised quantum circuits: Quantum Neural Network (discriminative QML model) and Quantum Circuit Born Machine (generative QML model)

We propose to use a special type of generative neural networks - a Restricted Boltzmann Machine (RBM) - to build a powerful generator of synthetic market data that can replicate the probability distribution of the original market data. An RBM constructed with stochastic binary activation units...

This paper discusses the implications of having risk management systems built on simplified methodologies. As an example, quanto adjustments for risk factors simulation are considered. The impact on counterparty exposure and regulatory capital calculations is quantified.