Autoencoders for Financial Anomaly Detection: A Review of Architectures, Evaluation Practice and Deployment Gaps
Financial institutions must decide, within the milliseconds of a payment authorisation window and on evidence that is almost entirely unlabelled, whether a transaction is fraudulent: positives account for less than 0.2% of records, confirmatory labels arrive months later as chargebacks, and the gene...
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Reference entry |
| Lenguaje: | inglés |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | Enlace permanente (DOI o Handle) |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1881700531369410560 |
|---|---|
| author | Alexander Haro-Sarango Diana Castillo‐Martínez Silvia Cachay-Salcedo Jessica Karina Saavedra-Vasconez Rosa Salcedo-Dávalos Briseida Sotelo-Castro Carlos Saavedra-Vasconez |
| author_browse | Alexander Haro-Sarango Briseida Sotelo-Castro Carlos Saavedra-Vasconez Diana Castillo‐Martínez Jessica Karina Saavedra-Vasconez Rosa Salcedo-Dávalos Silvia Cachay-Salcedo |
| author_facet | Alexander Haro-Sarango Diana Castillo‐Martínez Silvia Cachay-Salcedo Jessica Karina Saavedra-Vasconez Rosa Salcedo-Dávalos Briseida Sotelo-Castro Carlos Saavedra-Vasconez |
| author_sort | Alexander Haro-Sarango |
| collection | Producción científica |
| description | Financial institutions must decide, within the milliseconds of a payment authorisation window and on evidence that is almost entirely unlabelled, whether a transaction is fraudulent: positives account for less than 0.2% of records, confirmatory labels arrive months later as chargebacks, and the generating process adapts to whatever boundary a detector exposes. Supervised classification is poorly posed under these conditions. An autoencoder is a neural network trained to reconstruct its own input through a low-dimensional bottleneck; fitted to legitimate transactions alone, it converts an intractable labelling problem into a tractable one-class fitting problem, and the reconstruction error of a new record becomes a continuous score of atypicality. This review synthesises 85 Scopus-indexed records published between 2018 and 2026. It describes eleven architectural families and their hybridisation with resampling schemes, tree ensembles, one-class classifiers, and generative models across card payments, transaction monitoring, accounting and audit records, insurance claims, anti-money laundering screening, and on-chain value transfers. It then examines how these detectors are evaluated and finds the design space broad in architecture and narrow in evaluation: threshold selection, temporally held-out validation, drift analysis, and latency reporting are absent from almost every record examined. Closing those gaps, rather than adding architectural variants, is the priority the literature indicates. |
| format | Reference entry |
| id | openalex:W7223005835 |
| institution | UPeU |
| language | English |
| publishDate | 2026 |
| publishDateRange | 2026 |
| publishDateSort | 2026 |
| record_format | dspace |
| spelling | openalex:W7223005835Autoencoders for Financial Anomaly Detection: A Review of Architectures, Evaluation Practice and Deployment GapsAlexander Haro-SarangoDiana Castillo‐MartínezSilvia Cachay-SalcedoJessica Karina Saavedra-VasconezRosa Salcedo-DávalosBriseida Sotelo-CastroCarlos Saavedra-Vasconezautoencoderfinancial anomaly detectionfraud detectionone-class classificationreconstruction errorcard paymentstransaction monitoringanti-money launderinginsurance claimsaudit logsgenerative modelsresamplingevaluation metricstemporal driftclass imbalanceAnomaly Detection Techniques and ApplicationsImbalanced Data Classification TechniquesNetwork Security and Intrusion DetectionFinancial institutions must decide, within the milliseconds of a payment authorisation window and on evidence that is almost entirely unlabelled, whether a transaction is fraudulent: positives account for less than 0.2% of records, confirmatory labels arrive months later as chargebacks, and the generating process adapts to whatever boundary a detector exposes. Supervised classification is poorly posed under these conditions. An autoencoder is a neural network trained to reconstruct its own input through a low-dimensional bottleneck; fitted to legitimate transactions alone, it converts an intractable labelling problem into a tractable one-class fitting problem, and the reconstruction error of a new record becomes a continuous score of atypicality. This review synthesises 85 Scopus-indexed records published between 2018 and 2026. It describes eleven architectural families and their hybridisation with resampling schemes, tree ensembles, one-class classifiers, and generative models across card payments, transaction monitoring, accounting and audit records, insurance claims, anti-money laundering screening, and on-chain value transfers. It then examines how these detectors are evaluated and finds the design space broad in architecture and narrow in evaluation: threshold selection, temporally held-out validation, drift analysis, and latency reporting are absent from almost every record examined. Closing those gaps, rather than adding architectural variants, is the priority the literature indicates.Reference entryhttps://doi.org/10.3390/encyclopedia6100233W7223005835enEncyclopedia2673-83922026-10-20 |
| spellingShingle | autoencoder financial anomaly detection fraud detection one-class classification reconstruction error card payments transaction monitoring anti-money laundering insurance claims audit logs generative models resampling evaluation metrics temporal drift class imbalance Anomaly Detection Techniques and Applications Imbalanced Data Classification Techniques Network Security and Intrusion Detection Alexander Haro-Sarango Diana Castillo‐Martínez Silvia Cachay-Salcedo Jessica Karina Saavedra-Vasconez Rosa Salcedo-Dávalos Briseida Sotelo-Castro Carlos Saavedra-Vasconez Autoencoders for Financial Anomaly Detection: A Review of Architectures, Evaluation Practice and Deployment Gaps |
| title | Autoencoders for Financial Anomaly Detection: A Review of Architectures, Evaluation Practice and Deployment Gaps |
| title_full | Autoencoders for Financial Anomaly Detection: A Review of Architectures, Evaluation Practice and Deployment Gaps |
| title_fullStr | Autoencoders for Financial Anomaly Detection: A Review of Architectures, Evaluation Practice and Deployment Gaps |
| title_full_unstemmed | Autoencoders for Financial Anomaly Detection: A Review of Architectures, Evaluation Practice and Deployment Gaps |
| title_short | Autoencoders for Financial Anomaly Detection: A Review of Architectures, Evaluation Practice and Deployment Gaps |
| title_sort | autoencoders for financial anomaly detection a review of architectures evaluation practice and deployment gaps |
| topic | autoencoder financial anomaly detection fraud detection one-class classification reconstruction error card payments transaction monitoring anti-money laundering insurance claims audit logs generative models resampling evaluation metrics temporal drift class imbalance Anomaly Detection Techniques and Applications Imbalanced Data Classification Techniques Network Security and Intrusion Detection |
| topic_facet | autoencoder financial anomaly detection fraud detection one-class classification reconstruction error card payments transaction monitoring anti-money laundering insurance claims audit logs generative models resampling evaluation metrics temporal drift class imbalance Anomaly Detection Techniques and Applications Imbalanced Data Classification Techniques Network Security and Intrusion Detection |
| url | https://doi.org/10.3390/encyclopedia6100233 |
| work_keys_str_mv | AT alexanderharosarango autoencodersforfinancialanomalydetectionareviewofarchitecturesevaluationpracticeanddeploymentgaps AT dianacastillomartinez autoencodersforfinancialanomalydetectionareviewofarchitecturesevaluationpracticeanddeploymentgaps AT silviacachaysalcedo autoencodersforfinancialanomalydetectionareviewofarchitecturesevaluationpracticeanddeploymentgaps AT jessicakarinasaavedravasconez autoencodersforfinancialanomalydetectionareviewofarchitecturesevaluationpracticeanddeploymentgaps AT rosasalcedodavalos autoencodersforfinancialanomalydetectionareviewofarchitecturesevaluationpracticeanddeploymentgaps AT briseidasotelocastro autoencodersforfinancialanomalydetectionareviewofarchitecturesevaluationpracticeanddeploymentgaps AT carlossaavedravasconez autoencodersforfinancialanomalydetectionareviewofarchitecturesevaluationpracticeanddeploymentgaps |