We investigate the performance of the Deep Hedging framework under training paths beyond the (finite dimensional) Markovian setup. In particular we analyse the hedging performance of the original architecture under rough volatility models with view to existing theoretical results for those....

This study presents an extension of the Gaussian process regression model for multiple-input multiple-output forecasting. This approach allows modelling the cross-dependencies between a given set of input variables and generating a vectorial prediction. Making use of the existing correlations in...

Modeling counterparty risk is computationally challenging because it requires the simultaneous evaluation of all the trades with each counterparty under both market and credit risk. We present a multi-Gaussian process regression approach, which is well suited for OTC derivative portfolio...

We develop a new method that detects jumps nonparametrically in financial time series and significantly outperforms the current benchmark on simulated data. We use a long short- term memory (LSTM) neural network that is trained on labelled data generated by a process that experiences both jumps...

We suggest a theoretical basis for the comparative evaluation of forecasts. Instead of the general assumption that the data is generated from a stochastic model, we classify three stages of prediction experiments: pure non-stochastic prediction of given data, stochastic prediction of given data,...

Population forecasts are crucial for many social, political and economic decisions. Official population projections rely in general on deterministic models which use different scenarios for future vital rates to indicate uncertainty. However, this technique shows substantial weak points such as...