2020
DOI: 10.4018/jdm.2020010104
|View full text |Cite
|
Sign up to set email alerts
|

A Service Architecture Using Machine Learning to Contextualize Anomaly Detection

Abstract: This article introduces a service that helps provide context and an explanation for the outlier score given to any network flow record selected by the analyst. The authors propose a service architecture for the delivery of contextual information related to network flow records. The service constructs a set of contexts for the record using features including the host addresses, the application in use and the time of the event. For each context the service will find the nearest neighbors of the record, analyze t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 10 publications
(8 citation statements)
references
References 42 publications
0
6
0
Order By: Relevance
“…Within XAI literature, researchers have tried to assess the impact of explanations on the decision-making of fraud experts working with AI models in domains such as intrusion detection, fraudulent warranty claims, and banking transaction frauds. In [38], the authors provide a service architecture for security experts with explanations, aiming This is an open access post-print version; the final authenticated version is available online at https://link.springer.com/chapter/10.1007/978-3-030-57321-8_18 by © IFIP International Federation for Information Processing 2020.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…Within XAI literature, researchers have tried to assess the impact of explanations on the decision-making of fraud experts working with AI models in domains such as intrusion detection, fraudulent warranty claims, and banking transaction frauds. In [38], the authors provide a service architecture for security experts with explanations, aiming This is an open access post-print version; the final authenticated version is available online at https://link.springer.com/chapter/10.1007/978-3-030-57321-8_18 by © IFIP International Federation for Information Processing 2020.…”
Section: Related Workmentioning
confidence: 99%
“…In summary, it is observed in [38,39,41,42] proposals aiming for the integration of explanations in a fraud detection context. Within visual analytics literature, it is also observed studies aiming to support the decision-making of fraud experts through visualizations [21,45,46].…”
Section: Related Workmentioning
confidence: 99%
“…In summary, prior studies on credit risk assessment models for financial institutions focus on improving imbalanced data or classification accuracy through multistage modeling and DL. Although these methods can somewhat boost accuracy, the following aspects need to be further addressed: low time responsiveness, transparency, interpretability, and analysis of behavior features (Laughlin, Sankaranarayanan, & El-Khatib, 2020).…”
Section: Literature Reviewmentioning
confidence: 99%
“…Previous studies employing XAI and EM for fraud detection explore the effects and performance of explanations in fraud expert's work. In [31], authors provide a service architecture for security experts with explanations, aiming to introduce more context for the outlier score given anomalous records of network flows. In [12], authors provide experts with Shapley Additive Explanations (SHAP) [34] for why particular warranty claims are marked as anomalies by a machine learning (ML) model.…”
Section: Theoretical Foundation and Related Workmentioning
confidence: 99%