Sleuthing for adverse outcomes: Using anomaly detection to identify unusual behaviors of third-party agents

Michelle Miller, Robert Cezeaux
Proceedings of the KDD 2017: Workshop on Anomaly Detection in Finance, PMLR 71:121-125, 2018.

Abstract

Business transactions between customers and financing entities are often governed by intermediary agents. In this scenario, actions taken by these agents can affect the likelihood of adverse outcomes for both the customers and the financial institution. Our goal is to establish a general framework that identifies these types of anomalous agents. In this paper, we demonstrate a novel application of anomaly detection using isolation forests to identify which agents may be associated with adverse outcomes. We apply a genetic algorithm to understand which features were key to the performance of anomaly detection and and suggest a general framework for problems that similarly concern the behaviors of third-party agents.

Cite this Paper

BibTeX
@InProceedings{pmlr-v71-miller18a, title = {Sleuthing for adverse outcomes: Using anomaly detection to identify unusual behaviors of third-party agents}, author = {Miller, Michelle and Cezeaux, Robert}, booktitle = {Proceedings of the KDD 2017: Workshop on Anomaly Detection in Finance}, pages = {121--125}, year = {2018}, editor = {Anandakrishnan, Archana and Kumar, Senthil and Statnikov, Alexander and Faruquie, Tanveer and Xu, Di}, volume = {71}, series = {Proceedings of Machine Learning Research}, month = {14 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v71/miller18a/miller18a.pdf}, url = {https://proceedings.mlr.press/v71/miller18a.html}, abstract = {Business transactions between customers and financing entities are often governed by intermediary agents. In this scenario, actions taken by these agents can affect the likelihood of adverse outcomes for both the customers and the financial institution. Our goal is to establish a general framework that identifies these types of anomalous agents. In this paper, we demonstrate a novel application of anomaly detection using isolation forests to identify which agents may be associated with adverse outcomes. We apply a genetic algorithm to understand which features were key to the performance of anomaly detection and and suggest a general framework for problems that similarly concern the behaviors of third-party agents.} }
Endnote
%0 Conference Paper %T Sleuthing for adverse outcomes: Using anomaly detection to identify unusual behaviors of third-party agents %A Michelle Miller %A Robert Cezeaux %B Proceedings of the KDD 2017: Workshop on Anomaly Detection in Finance %C Proceedings of Machine Learning Research %D 2018 %E Archana Anandakrishnan %E Senthil Kumar %E Alexander Statnikov %E Tanveer Faruquie %E Di Xu %F pmlr-v71-miller18a %I PMLR %P 121--125 %U https://proceedings.mlr.press/v71/miller18a.html %V 71 %X Business transactions between customers and financing entities are often governed by intermediary agents. In this scenario, actions taken by these agents can affect the likelihood of adverse outcomes for both the customers and the financial institution. Our goal is to establish a general framework that identifies these types of anomalous agents. In this paper, we demonstrate a novel application of anomaly detection using isolation forests to identify which agents may be associated with adverse outcomes. We apply a genetic algorithm to understand which features were key to the performance of anomaly detection and and suggest a general framework for problems that similarly concern the behaviors of third-party agents.
APA
Miller, M. & Cezeaux, R.. (2018). Sleuthing for adverse outcomes: Using anomaly detection to identify unusual behaviors of third-party agents. Proceedings of the KDD 2017: Workshop on Anomaly Detection in Finance, in Proceedings of Machine Learning Research 71:121-125 Available from https://proceedings.mlr.press/v71/miller18a.html.

Related Material