Event-Based Historical Value-at-Risk

Frederik Hogenboom; M de Winter; M Jansen; Alexander Hogenboom; Flavius Frasincar; U Kaymak

doi:10.1109/CIFEr.2012.6327787

Event-Based Historical Value-at-Risk

Frederik Hogenboom, M de Winter, M Jansen, Alexander Hogenboom, Flavius Frasincar, U Kaymak

Research output: Chapter/Conference proceeding › Conference proceeding › Academic › peer-review

3 Citations (Scopus)

Abstract

Value-at-Risk (VaR) is an important tool to assess portfolio risk. When calculating VaR based on historical stock return data, we hypothesize that this historical data is sensitive to outliers caused by news events in the sampled period. In this paper, we research whether the VaR accuracy can be improved by considering news events as additional input in the calculation. This involves processing the historical data in order to reflect the impact of news on the stock returns. Our experiments show that when an event occurs, removing the noise (that is caused by an event) from the measured stock prices for a small time window can improve VaR predictions.

Original language	English
Title of host publication	IEEE Computational Intelligence for Financial Engineering & Economics 2012 (CIFEr 2012)
Place of Publication	New York City, New York, USA
Pages	164-170
Number of pages	7
DOIs	https://doi.org/10.1109/CIFEr.2012.6327787
Publication status	Published - 29 Mar 2012

Research programs

EUR ESE 32

Access to Document

10.1109/CIFEr.2012.6327787

http://hdl.handle.net/1765/86221

Cite this

@inproceedings{c51aeffd8c974c6ab1f93706840a6fb1,

title = "Event-Based Historical Value-at-Risk",

abstract = "Value-at-Risk (VaR) is an important tool to assess portfolio risk. When calculating VaR based on historical stock return data, we hypothesize that this historical data is sensitive to outliers caused by news events in the sampled period. In this paper, we research whether the VaR accuracy can be improved by considering news events as additional input in the calculation. This involves processing the historical data in order to reflect the impact of news on the stock returns. Our experiments show that when an event occurs, removing the noise (that is caused by an event) from the measured stock prices for a small time window can improve VaR predictions.",

author = "Frederik Hogenboom and {de Winter}, M and M Jansen and Alexander Hogenboom and Flavius Frasincar and U Kaymak",

year = "2012",

month = mar,

day = "29",

doi = "10.1109/CIFEr.2012.6327787",

language = "English",

pages = "164--170",

booktitle = "IEEE Computational Intelligence for Financial Engineering & Economics 2012 (CIFEr 2012)",

}

TY - GEN

T1 - Event-Based Historical Value-at-Risk

AU - Hogenboom, Frederik

AU - de Winter, M

AU - Jansen, M

AU - Hogenboom, Alexander

AU - Frasincar, Flavius

AU - Kaymak, U

PY - 2012/3/29

Y1 - 2012/3/29

N2 - Value-at-Risk (VaR) is an important tool to assess portfolio risk. When calculating VaR based on historical stock return data, we hypothesize that this historical data is sensitive to outliers caused by news events in the sampled period. In this paper, we research whether the VaR accuracy can be improved by considering news events as additional input in the calculation. This involves processing the historical data in order to reflect the impact of news on the stock returns. Our experiments show that when an event occurs, removing the noise (that is caused by an event) from the measured stock prices for a small time window can improve VaR predictions.

AB - Value-at-Risk (VaR) is an important tool to assess portfolio risk. When calculating VaR based on historical stock return data, we hypothesize that this historical data is sensitive to outliers caused by news events in the sampled period. In this paper, we research whether the VaR accuracy can be improved by considering news events as additional input in the calculation. This involves processing the historical data in order to reflect the impact of news on the stock returns. Our experiments show that when an event occurs, removing the noise (that is caused by an event) from the measured stock prices for a small time window can improve VaR predictions.

U2 - 10.1109/CIFEr.2012.6327787

DO - 10.1109/CIFEr.2012.6327787

M3 - Conference proceeding

SP - 164

EP - 170

BT - IEEE Computational Intelligence for Financial Engineering & Economics 2012 (CIFEr 2012)

CY - New York City, New York, USA

ER -

Event-Based Historical Value-at-Risk

Abstract

Research programs

Access to Document

Fingerprint

Cite this