Detecting anomalous payments networks: A dimensionality-reduction approach
Anomaly-detection methods are aimed at identifying observations that deviate manifestly from what is expected. Such methods are usually run on low-dimensional data, such as time series data. However, the increasing importance of high-dimensional payments and exposure data for financial oversight req...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-01-01
|
| Series: | Latin American Journal of Central Banking |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666143820300016 |
| _version_ | 1818865335490576384 |
|---|---|
| author | Carlos León |
| author_facet | Carlos León |
| author_sort | Carlos León |
| collection | DOAJ |
| description | Anomaly-detection methods are aimed at identifying observations that deviate manifestly from what is expected. Such methods are usually run on low-dimensional data, such as time series data. However, the increasing importance of high-dimensional payments and exposure data for financial oversight requires methods for detecting anomalous networks. To detect an anomalous network, dimensionality reduction allows measuring of the extent to which the network's main connective features (i.e. the structure) deviate from those regarded as typical. The key to dimensionality-reduction methods is the ability to reconstruct data with an error; this reconstruction error serves as a yardstick for deviation from what is typical. Principal component analysis (PCA) is used as a dimensionality-reduction method, and a clustering algorithm is used to classify reconstruction errors as normal or anomalous. Based on data from Colombia's large-value payments system and a set of synthetic anomalous networks created through simulations of intraday payments, detecting anomalous payments networks is feasible and promising for financial-oversight purposes. |
| first_indexed | 2024-12-19T10:45:55Z |
| format | Article |
| id | doaj.art-0a7299e63e38410eb6e7a413aa9f8f1b |
| institution | Directory Open Access Journal |
| issn | 2666-1438 |
| language | English |
| last_indexed | 2024-12-19T10:45:55Z |
| publishDate | 2020-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Latin American Journal of Central Banking |
| spelling | doaj.art-0a7299e63e38410eb6e7a413aa9f8f1b2022-12-21T20:25:16ZengElsevierLatin American Journal of Central Banking2666-14382020-01-0111100001Detecting anomalous payments networks: A dimensionality-reduction approachCarlos León0Financial Infrastructure Oversight Department, Banco de la República, Bogotá, Colombia; Department of Finance, Tilburg University, Tilburg, The NetherlandsAnomaly-detection methods are aimed at identifying observations that deviate manifestly from what is expected. Such methods are usually run on low-dimensional data, such as time series data. However, the increasing importance of high-dimensional payments and exposure data for financial oversight requires methods for detecting anomalous networks. To detect an anomalous network, dimensionality reduction allows measuring of the extent to which the network's main connective features (i.e. the structure) deviate from those regarded as typical. The key to dimensionality-reduction methods is the ability to reconstruct data with an error; this reconstruction error serves as a yardstick for deviation from what is typical. Principal component analysis (PCA) is used as a dimensionality-reduction method, and a clustering algorithm is used to classify reconstruction errors as normal or anomalous. Based on data from Colombia's large-value payments system and a set of synthetic anomalous networks created through simulations of intraday payments, detecting anomalous payments networks is feasible and promising for financial-oversight purposes.http://www.sciencedirect.com/science/article/pii/S2666143820300016Anomaly detectionPaymentsNetworkDimensionalityClustering |
| spellingShingle | Carlos León Detecting anomalous payments networks: A dimensionality-reduction approach Latin American Journal of Central Banking Anomaly detection Payments Network Dimensionality Clustering |
| title | Detecting anomalous payments networks: A dimensionality-reduction approach |
| title_full | Detecting anomalous payments networks: A dimensionality-reduction approach |
| title_fullStr | Detecting anomalous payments networks: A dimensionality-reduction approach |
| title_full_unstemmed | Detecting anomalous payments networks: A dimensionality-reduction approach |
| title_short | Detecting anomalous payments networks: A dimensionality-reduction approach |
| title_sort | detecting anomalous payments networks a dimensionality reduction approach |
| topic | Anomaly detection Payments Network Dimensionality Clustering |
| url | http://www.sciencedirect.com/science/article/pii/S2666143820300016 |
| work_keys_str_mv | AT carlosleon detectinganomalouspaymentsnetworksadimensionalityreductionapproach |