Detecting anomalous WM/reuters fixes using Trailing Contextual Anomaly Detection

Gbenga Ibikunle; Vito Mollica; Qiao Sun

doi:10.1016/j.iref.2024.103512

Detecting anomalous WM/reuters fixes using Trailing Contextual Anomaly Detection

Gbenga Ibikunle, Vito Mollica, Qiao Sun^*

^*Corresponding author for this work

Macquarie Graduate School of Management

Research output: Contribution to journal › Article › peer-review

115 Downloads (Pure)

Abstract

We propose a Trailing Contextual Anomaly Detection (TCAD) model to detect abnormal movements in the WM/Reuters foreign exchange benchmark setting. By leveraging the high correlation levels among currencey pairs, we demonstrate that the TCAD model outperforms ARIMA, Jump Test, and CAD methods in detecting idiosyncratic cross-sectional anomalies. Additionally, we find that adjusting for intraday seasonality enhances the models' ability to predict on market close manipulation. Furthermore, we quantify and identify abnormal fix movements as high-impact events.

Original language	English
Article number	103512
Pages (from-to)	1-21
Number of pages	21
Journal	International Review of Economics and Finance
Volume	96
DOIs	https://doi.org/10.1016/j.iref.2024.103512
Publication status	Published - Nov 2024

Bibliographical note

© 2024 The Authors. Published by Elsevier Inc. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

Anomalies in price
Comovement
Foreign exchange markets
Market manipulation

Access to Document

10.1016/j.iref.2024.103512Licence: CC BY-NC

Publisher version (open access)Final published version, 4.47 MBLicence: CC BY-NC

Cite this

@article{5c43b50703e84c528630b2adcfef8ada,

title = "Detecting anomalous WM/reuters fixes using Trailing Contextual Anomaly Detection",

abstract = "We propose a Trailing Contextual Anomaly Detection (TCAD) model to detect abnormal movements in the WM/Reuters foreign exchange benchmark setting. By leveraging the high correlation levels among currencey pairs, we demonstrate that the TCAD model outperforms ARIMA, Jump Test, and CAD methods in detecting idiosyncratic cross-sectional anomalies. Additionally, we find that adjusting for intraday seasonality enhances the models' ability to predict on market close manipulation. Furthermore, we quantify and identify abnormal fix movements as high-impact events.",

keywords = "Anomalies in price, Comovement, Foreign exchange markets, Market manipulation",

author = "Gbenga Ibikunle and Vito Mollica and Qiao Sun",

note = "{\textcopyright} 2024 The Authors. Published by Elsevier Inc. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher. ",

year = "2024",

month = nov,

doi = "10.1016/j.iref.2024.103512",

language = "English",

volume = "96",

pages = "1--21",

journal = "International Review of Economics and Finance",

issn = "1059-0560",

publisher = "Elsevier",

}

TY - JOUR

T1 - Detecting anomalous WM/reuters fixes using Trailing Contextual Anomaly Detection

AU - Ibikunle, Gbenga

AU - Mollica, Vito

AU - Sun, Qiao

N1 - © 2024 The Authors. Published by Elsevier Inc. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2024/11

Y1 - 2024/11

N2 - We propose a Trailing Contextual Anomaly Detection (TCAD) model to detect abnormal movements in the WM/Reuters foreign exchange benchmark setting. By leveraging the high correlation levels among currencey pairs, we demonstrate that the TCAD model outperforms ARIMA, Jump Test, and CAD methods in detecting idiosyncratic cross-sectional anomalies. Additionally, we find that adjusting for intraday seasonality enhances the models' ability to predict on market close manipulation. Furthermore, we quantify and identify abnormal fix movements as high-impact events.

AB - We propose a Trailing Contextual Anomaly Detection (TCAD) model to detect abnormal movements in the WM/Reuters foreign exchange benchmark setting. By leveraging the high correlation levels among currencey pairs, we demonstrate that the TCAD model outperforms ARIMA, Jump Test, and CAD methods in detecting idiosyncratic cross-sectional anomalies. Additionally, we find that adjusting for intraday seasonality enhances the models' ability to predict on market close manipulation. Furthermore, we quantify and identify abnormal fix movements as high-impact events.

KW - Anomalies in price

KW - Comovement

KW - Foreign exchange markets

KW - Market manipulation

UR - https://www.scopus.com/pages/publications/85202548233

U2 - 10.1016/j.iref.2024.103512

DO - 10.1016/j.iref.2024.103512

M3 - Article

AN - SCOPUS:85202548233

SN - 1059-0560

VL - 96

SP - 1

EP - 21

JO - International Review of Economics and Finance

JF - International Review of Economics and Finance

M1 - 103512

ER -

Detecting anomalous WM/reuters fixes using Trailing Contextual Anomaly Detection

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this