Loading...
Paper Type
ERF
Description
Outlier detection is widely used for identification of unusual suspicious patterns in health care fraud detection. However, the impact of adversarial perturbations on outliers and the related decisions are not well studied. In the health care fraud detection domain, standard practice does not consider health care billings being subject to intentional data manipulations. This paper presents a decision theoretic approach for outlier detection in adversarial environments. Proposed adversarial risk analysis-based framework allows incomplete information and adversarial perturbations on the data inputs. While the work with actual health care fraud data is ongoing, the proposed novel adversarial outlier detection method has the potential to support health care fraud audit decision support systems.
Paper Number
1045
Recommended Citation
Ekin, Tahir, "Adversarial Outlier Detection Methods for Health Care Fraud" (2023). AMCIS 2023 Proceedings. 2.
https://aisel.aisnet.org/amcis2023/sig_dsa/sig_dsa/2
Adversarial Outlier Detection Methods for Health Care Fraud
Outlier detection is widely used for identification of unusual suspicious patterns in health care fraud detection. However, the impact of adversarial perturbations on outliers and the related decisions are not well studied. In the health care fraud detection domain, standard practice does not consider health care billings being subject to intentional data manipulations. This paper presents a decision theoretic approach for outlier detection in adversarial environments. Proposed adversarial risk analysis-based framework allows incomplete information and adversarial perturbations on the data inputs. While the work with actual health care fraud data is ongoing, the proposed novel adversarial outlier detection method has the potential to support health care fraud audit decision support systems.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
SIG DSA