---
_id: '66449'
abstract:
- lang: eng
  text: "This paper evaluates the forecasting performance of an expanded class of
    (semi-)parametric \r\nGARCH models belonging to the EGARCH family (EGF), including
    recently introduced long  \r\nand short memory specifications and their semiparametric
    extensions. The semiparametric \r\nvariants employ a multiplicative volatility
    decomposition into conditional and slowly varying \r\nunconditional components,
    where the latter is estimated via a data-driven local polynomial \r\nsmoother
    to accommodate non-stationarities commonly observed in financial time series.
    Based \r\non the revised Basel Committee framework for market-risk assessment,
    all models are capable \r\nof producing rolling one-day-ahead forecasts for Value
    at Risk (VaR) and Expected Shortfall \r\n(ES) under a wide range of symmetric
    and skewed innovation distributions. Their forecasting \r\naccuracy is examined
    using the regulatory traffic light tests for VaR and the recently developed \r\nES-specific
    traffic light procedure, complemented by the regulatory loss function. In addition,
    \r\nmodel selection incorporates both a recently proposed corrected firm-oriented
    loss function that \r\naccounts for opportunity costs and the Weighted Absolute
    Deviation (WAD) criterion. The \r\nempirical comparison demonstrates that (semiparametric)
    long memory GARCH models - \r\nparticularly those combining fractional dynamics
    with nonparametric scale adjustments - can \r\nserve as valuable alternatives
    to traditional parametric short memory models, offering more \r\nstable volatility
    estimates and improved tail-risk forecasts for practical risk management \r\napplications."
author:
- first_name: Dominik Christian
  full_name: Hanke, Dominik Christian
  id: '63677'
  last_name: Hanke
- first_name: André
  full_name: Uhde, André
  id: '36049'
  last_name: Uhde
- first_name: Yuanhua
  full_name: Feng, Yuanhua
  id: '20760'
  last_name: Feng
citation:
  ama: Hanke DC, Uhde A, Feng Y. <i>Application of Novel Exponential (Semi-)Parametric
    Short and Long  Memory GARCH Models under Regulatory Requirements of Basel III</i>.;
    2026.
  apa: Hanke, D. C., Uhde, A., &#38; Feng, Y. (2026). <i>Application of Novel Exponential
    (Semi-)Parametric Short and Long  Memory GARCH Models under Regulatory Requirements
    of Basel III</i>.
  bibtex: '@book{Hanke_Uhde_Feng_2026, title={Application of Novel Exponential (Semi-)Parametric
    Short and Long  Memory GARCH Models under Regulatory Requirements of Basel III},
    author={Hanke, Dominik Christian and Uhde, André and Feng, Yuanhua}, year={2026}
    }'
  chicago: Hanke, Dominik Christian, André Uhde, and Yuanhua Feng. <i>Application
    of Novel Exponential (Semi-)Parametric Short and Long  Memory GARCH Models under
    Regulatory Requirements of Basel III</i>, 2026.
  ieee: D. C. Hanke, A. Uhde, and Y. Feng, <i>Application of Novel Exponential (Semi-)Parametric
    Short and Long  Memory GARCH Models under Regulatory Requirements of Basel III</i>.
    2026.
  mla: Hanke, Dominik Christian, et al. <i>Application of Novel Exponential (Semi-)Parametric
    Short and Long  Memory GARCH Models under Regulatory Requirements of Basel III</i>.
    2026.
  short: D.C. Hanke, A. Uhde, Y. Feng, Application of Novel Exponential (Semi-)Parametric
    Short and Long  Memory GARCH Models under Regulatory Requirements of Basel III,
    2026.
date_created: 2026-07-13T09:21:49Z
date_updated: 2026-07-16T09:07:19Z
ddc:
- '330'
department:
- _id: '200'
- _id: '186'
file:
- access_level: open_access
  content_type: application/pdf
  creator: dhanke
  date_created: 2026-07-13T09:21:45Z
  date_updated: 2026-07-13T09:21:45Z
  file_id: '66450'
  file_name: TAF_WP_105_HankeUhdeFeng2026.pdf
  file_size: 1830858
  relation: main_file
file_date_updated: 2026-07-13T09:21:45Z
has_accepted_license: '1'
jel:
- C22
- C4
- C5
- C6
- B26
keyword:
- semiparametric GARCH extension
- data-driven local polynomial smoother
- long  memory
- GARCH models
- Value at Risk
- Expected Shortfall
- traffic light test
- backtesting
- Basel  III
- market risk
language:
- iso: eng
oa: '1'
status: public
title: Application of Novel Exponential (Semi-)Parametric Short and Long  Memory GARCH
  Models under Regulatory Requirements of Basel III
type: working_paper
user_id: '63677'
year: '2026'
...