We propose how deep neural networks can be used to calibrate the parameters of Stochastic-Volatility Jump-Diffusion (SVJD) models to historical asset return time series. 1-Dimensional Convolutional Neural Networks (1D-CNN) are used for that purpose. The accuracy of the deep learning approach is...

We investigate valuation of derivatives with payoff defined as a nonlinear though close to linear function of tradable underlying assets. Interest rate derivatives involving Libor or swap rates in arrears, i.e. rates paid at wrong time, are a typical example. It is generally tempting to replace...

Market value of derivatives after crisis requires discounting with interest rates that take into account the credit risk of the involved counterparties of the trade. The increase of credit risk is evidenced by the presence of basis swap spreads. Using one curve to both estimating the forward...

The paper proposes an application of the survival time analysis methodology to estimations of the Loss Given Default (LGD) parameter. The main advantage of the survival analysis approach compared to classical regression methods is that it allows exploiting partial recovery data. The model is...

The Basle II parameter called Loss Given Default (LGD) aims to estimate the expected losses on not yet defaulted accounts in the case of default. Banks firstly need to collect historical recovery data, discount the recovery income and cost cash flow to the time of default, and calculate...