English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In the financial services industry, forecasting the risk factor distributionconditional on the history and the current market environment is the key tomarket risk modeling in general and value at risk (VaR) model in particular. Asone of the most widely adopted VaR models in commercial banks, Historicalsimulation (HS) uses the empirical distribution of daily returns in ahistorical window as the forecast distribution of risk factor returns in thenext day. The objectives for financial time series generation are to generatesynthetic data paths with good variety, and similar distribution and dynamicsto the original historical data. In this paper, we apply multiple existing deepgenerative methods (e.g., CGAN, CWGAN, Diffusion, and Signature WGAN) forconditional time series generation, and propose and test two new methods forconditional multi-step time series generation, namely Encoder-Decoder CGAN andConditional TimeVAE. Furthermore, we introduce a comprehensive framework with aset of KPIs to measure the quality of the generated time series for financialmodeling. The KPIs cover distribution distance, autocorrelation andbacktesting. All models (HS, parametric and neural networks) are tested on bothhistorical USD yield curve data and additional data simulated from GARCH andCIR processes. The study shows that top performing models are HS, GARCH andCWGAN models. Future research directions in this area are also discussed.

Deep Generative Modeling for Financial Time Series with Application in VaR: A Comparative Review