Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data

Dallas Thornton, Guido van Capelleveen, Mannes Poel, Jos van Hillegersberg, Roland Mueller

  • 5 Citations

Abstract

Fraud, waste, and abuse in the U.S. healthcare system are estimated at $700 billion annually. Predictive analytics offers government and private payers the opportunity to identify and prevent or recover such billings. This paper proposes a data-driven method for fraud detection based on comparative research, fraud cases, and literature review. Unsupervised data mining techniques such as outlier detection are suggested as effective predictors for fraud. Based on a multi-dimensional data model developed for Medicaid claim data, specific metrics for dental providers were developed and evaluated in analytical experiments using outlier detection applied to claim, provider, and patient data in a state Medicaid program. The proposed methodology enabled successful identification of fraudulent activity, with 12 of the top 17 suspicious providers (71%) referred to officials for investigation with clearly anomalous and inappropriate activity. Future research is underway to extend the method to other specialties and enable its use by fraud analysts.
Original languageUndefined
Title of host publicationProceedings of the 16th International Conference on Enterprise Information Systems (ICEIS 2014)
PublisherSCITEPRESS
Pages684-694
Number of pages11
ISBN (Print)978-989-758-028-4
DOIs
StatePublished - Apr 2014
Event16th International Conference on Enterprise Information Systems, ICEIS 2014 - Lisbon, Portugal

Publication series

Name
PublisherScitepress

Conference

Conference16th International Conference on Enterprise Information Systems, ICEIS 2014
Abbreviated titleICEIS
CountryPortugal
CityLisbon
Period27/04/1430/04/14

Fingerprint

Data mining
Data structures
Experiments

Keywords

  • EWI-24984
  • Fraud detection
  • Medicaid
  • Healthcare Fraud
  • METIS-305987
  • IR-91956
  • Anomaly Detection
  • Data Mining
  • Outlier Detection

Cite this

Thornton, D., van Capelleveen, G., Poel, M., van Hillegersberg, J., & Mueller, R. (2014). Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data. In Proceedings of the 16th International Conference on Enterprise Information Systems (ICEIS 2014) (pp. 684-694). SCITEPRESS. DOI: 10.5220/0004986106840694

Thornton, Dallas; van Capelleveen, Guido; Poel, Mannes; van Hillegersberg, Jos; Mueller, Roland / Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data.

Proceedings of the 16th International Conference on Enterprise Information Systems (ICEIS 2014). SCITEPRESS, 2014. p. 684-694.

Research output: Scientific - peer-reviewConference contribution

@inbook{0ce5fddd6f3648e799fc34703c99d084,
title = "Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data",
abstract = "Fraud, waste, and abuse in the U.S. healthcare system are estimated at $700 billion annually. Predictive analytics offers government and private payers the opportunity to identify and prevent or recover such billings. This paper proposes a data-driven method for fraud detection based on comparative research, fraud cases, and literature review. Unsupervised data mining techniques such as outlier detection are suggested as effective predictors for fraud. Based on a multi-dimensional data model developed for Medicaid claim data, specific metrics for dental providers were developed and evaluated in analytical experiments using outlier detection applied to claim, provider, and patient data in a state Medicaid program. The proposed methodology enabled successful identification of fraudulent activity, with 12 of the top 17 suspicious providers (71%) referred to officials for investigation with clearly anomalous and inappropriate activity. Future research is underway to extend the method to other specialties and enable its use by fraud analysts.",
keywords = "EWI-24984, Fraud detection, Medicaid, Healthcare Fraud, METIS-305987, IR-91956, Anomaly Detection, Data Mining, Outlier Detection",
author = "Dallas Thornton and {van Capelleveen}, Guido and Mannes Poel and {van Hillegersberg}, Jos and Roland Mueller",
note = "10.5220/0004986106840694",
year = "2014",
month = "4",
doi = "10.5220/0004986106840694",
isbn = "978-989-758-028-4",
publisher = "SCITEPRESS",
pages = "684--694",
booktitle = "Proceedings of the 16th International Conference on Enterprise Information Systems (ICEIS 2014)",

}

Thornton, D, van Capelleveen, G, Poel, M, van Hillegersberg, J & Mueller, R 2014, Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data. in Proceedings of the 16th International Conference on Enterprise Information Systems (ICEIS 2014). SCITEPRESS, pp. 684-694, 16th International Conference on Enterprise Information Systems, ICEIS 2014, Lisbon, Portugal, 27-30 April. DOI: 10.5220/0004986106840694

Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data. / Thornton, Dallas; van Capelleveen, Guido; Poel, Mannes; van Hillegersberg, Jos; Mueller, Roland.

Proceedings of the 16th International Conference on Enterprise Information Systems (ICEIS 2014). SCITEPRESS, 2014. p. 684-694.

Research output: Scientific - peer-reviewConference contribution

TY - CHAP

T1 - Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data

AU - Thornton,Dallas

AU - van Capelleveen,Guido

AU - Poel,Mannes

AU - van Hillegersberg,Jos

AU - Mueller,Roland

N1 - 10.5220/0004986106840694

PY - 2014/4

Y1 - 2014/4

N2 - Fraud, waste, and abuse in the U.S. healthcare system are estimated at $700 billion annually. Predictive analytics offers government and private payers the opportunity to identify and prevent or recover such billings. This paper proposes a data-driven method for fraud detection based on comparative research, fraud cases, and literature review. Unsupervised data mining techniques such as outlier detection are suggested as effective predictors for fraud. Based on a multi-dimensional data model developed for Medicaid claim data, specific metrics for dental providers were developed and evaluated in analytical experiments using outlier detection applied to claim, provider, and patient data in a state Medicaid program. The proposed methodology enabled successful identification of fraudulent activity, with 12 of the top 17 suspicious providers (71%) referred to officials for investigation with clearly anomalous and inappropriate activity. Future research is underway to extend the method to other specialties and enable its use by fraud analysts.

AB - Fraud, waste, and abuse in the U.S. healthcare system are estimated at $700 billion annually. Predictive analytics offers government and private payers the opportunity to identify and prevent or recover such billings. This paper proposes a data-driven method for fraud detection based on comparative research, fraud cases, and literature review. Unsupervised data mining techniques such as outlier detection are suggested as effective predictors for fraud. Based on a multi-dimensional data model developed for Medicaid claim data, specific metrics for dental providers were developed and evaluated in analytical experiments using outlier detection applied to claim, provider, and patient data in a state Medicaid program. The proposed methodology enabled successful identification of fraudulent activity, with 12 of the top 17 suspicious providers (71%) referred to officials for investigation with clearly anomalous and inappropriate activity. Future research is underway to extend the method to other specialties and enable its use by fraud analysts.

KW - EWI-24984

KW - Fraud detection

KW - Medicaid

KW - Healthcare Fraud

KW - METIS-305987

KW - IR-91956

KW - Anomaly Detection

KW - Data Mining

KW - Outlier Detection

U2 - 10.5220/0004986106840694

DO - 10.5220/0004986106840694

M3 - Conference contribution

SN - 978-989-758-028-4

SP - 684

EP - 694

BT - Proceedings of the 16th International Conference on Enterprise Information Systems (ICEIS 2014)

PB - SCITEPRESS

ER -

Thornton D, van Capelleveen G, Poel M, van Hillegersberg J, Mueller R. Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data. In Proceedings of the 16th International Conference on Enterprise Information Systems (ICEIS 2014). SCITEPRESS. 2014. p. 684-694. Available from, DOI: 10.5220/0004986106840694