Anomaly Detection on Financial Time Series by Principal Component Analysis and Neural Networks

Stéphane Crépey (), Lehdili Noureddine, Nisrine Madhar () and Maud Thomas ()
Additional contact information
Stéphane Crépey: LPSM (UMR_8001) - Laboratoire de Probabilités, Statistique et Modélisation - SU - Sorbonne Université - CNRS - Centre National de la Recherche Scientifique - UPCité - Université Paris Cité, UPCité - Université Paris Cité
Lehdili Noureddine: Natixis
Nisrine Madhar: LPSM (UMR_8001) - Laboratoire de Probabilités, Statistique et Modélisation - SU - Sorbonne Université - CNRS - Centre National de la Recherche Scientifique - UPCité - Université Paris Cité, UPCité - Université Paris Cité, Natixis
Maud Thomas: LPSM (UMR_8001) - Laboratoire de Probabilités, Statistique et Modélisation - SU - Sorbonne Université - CNRS - Centre National de la Recherche Scientifique - UPCité - Université Paris Cité, SU - Sorbonne Université

Working Papers from HAL

Abstract: A major concern when dealing with financial time series involving a wide variety of market risk factors is the presence of anomalies. These induce a miscalibration of the models used to quantify and manage risk, resulting in potential erroneous risk measures. We propose an approach that aims to improve anomaly detection in financial time series, overcoming most of the inherent difficulties. Valuable features are extracted from the time series by compressing and reconstructing the data through principal component analysis. We then define an anomaly score using a feedforward neural network. A time series is considered to be contaminated when its anomaly score exceeds a given cutoff value. This cutoff value is not a hand-set parameter but rather is calibrated as a neural network parameter throughout the minimization of a customized loss function. The efficiency of the proposed approach compared to several well-known anomaly detection algorithms is numerically demonstrated on both synthetic and real data sets, with high and stable performance being achieved with the PCA NN approach. We show that value-at-risk estimation errors are reduced when the proposed anomaly detection model is used with a basic imputation approach to correct the anomaly.

Keywords: anomaly detection; financial time series; principal component analysis; neural network; density estimation; missing data; market risk; value at risk (search for similar items in EconPapers)
Date: 2022-10-24
New Economics Papers: this item is included in nep-big, nep-cmp and nep-rmg
Note: View the original document on HAL open archive server: https://hal.science/hal-03777995v3
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://hal.science/hal-03777995v3/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:wpaper:hal-03777995

Access Statistics for this paper

More papers in Working Papers from HAL
Bibliographic data for series maintained by CCSD ().