Explainable machine learning models for Medicare fraud detection
Abstract As a means of building explainable machine learning models for Big Data, we apply a novel ensemble supervised feature selection technique. The technique is applied to publicly available insurance claims data from the United States public health insurance program, Medicare. We approach Medic...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-10-01
|
| Series: | Journal of Big Data |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40537-023-00821-5 |
| _version_ | 1797559120366141440 |
|---|---|
| author | John T. Hancock Richard A. Bauder Huanjing Wang Taghi M. Khoshgoftaar |
| author_facet | John T. Hancock Richard A. Bauder Huanjing Wang Taghi M. Khoshgoftaar |
| author_sort | John T. Hancock |
| collection | DOAJ |
| description | Abstract As a means of building explainable machine learning models for Big Data, we apply a novel ensemble supervised feature selection technique. The technique is applied to publicly available insurance claims data from the United States public health insurance program, Medicare. We approach Medicare insurance fraud detection as a supervised machine learning task of anomaly detection through the classification of highly imbalanced Big Data. Our objectives for feature selection are to increase efficiency in model training, and to develop more explainable machine learning models for fraud detection. Using two Big Data datasets derived from two different sources of insurance claims data, we demonstrate how our feature selection technique reduces the dimensionality of the datasets by approximately 87.5% without compromising performance. Moreover, the reduction in dimensionality results in machine learning models that are easier to explain, and less prone to overfitting. Therefore, our primary contribution of the exposition of our novel feature selection technique leads to a further contribution to the application domain of automated Medicare insurance fraud detection. We utilize our feature selection technique to provide an explanation of our fraud detection models in terms of the definitions of the selected features. The ensemble supervised feature selection technique we present is flexible in that any collection of machine learning algorithms that maintain a list of feature importance values may be used. Therefore, researchers may easily employ variations of the technique we present. |
| first_indexed | 2024-03-10T17:40:55Z |
| format | Article |
| id | doaj.art-89c068cfa9654be2a0a8a7368f4bcc4f |
| institution | Directory Open Access Journal |
| issn | 2196-1115 |
| language | English |
| last_indexed | 2024-03-10T17:40:55Z |
| publishDate | 2023-10-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Big Data |
| spelling | doaj.art-89c068cfa9654be2a0a8a7368f4bcc4f2023-11-20T09:42:32ZengSpringerOpenJournal of Big Data2196-11152023-10-0110113110.1186/s40537-023-00821-5Explainable machine learning models for Medicare fraud detectionJohn T. Hancock0Richard A. Bauder1Huanjing Wang2Taghi M. Khoshgoftaar3College of Engineering and Computer Science, Florida Atlantic UniversityCollege of Engineering and Computer Science, Florida Atlantic UniversityOgden College of Science and Engineering, Western Kentucky UniversityCollege of Engineering and Computer Science, Florida Atlantic UniversityAbstract As a means of building explainable machine learning models for Big Data, we apply a novel ensemble supervised feature selection technique. The technique is applied to publicly available insurance claims data from the United States public health insurance program, Medicare. We approach Medicare insurance fraud detection as a supervised machine learning task of anomaly detection through the classification of highly imbalanced Big Data. Our objectives for feature selection are to increase efficiency in model training, and to develop more explainable machine learning models for fraud detection. Using two Big Data datasets derived from two different sources of insurance claims data, we demonstrate how our feature selection technique reduces the dimensionality of the datasets by approximately 87.5% without compromising performance. Moreover, the reduction in dimensionality results in machine learning models that are easier to explain, and less prone to overfitting. Therefore, our primary contribution of the exposition of our novel feature selection technique leads to a further contribution to the application domain of automated Medicare insurance fraud detection. We utilize our feature selection technique to provide an explanation of our fraud detection models in terms of the definitions of the selected features. The ensemble supervised feature selection technique we present is flexible in that any collection of machine learning algorithms that maintain a list of feature importance values may be used. Therefore, researchers may easily employ variations of the technique we present.https://doi.org/10.1186/s40537-023-00821-5Big DataClass imbalanceExplainable machine learning modelsEnsemble supervised feature selectionMedicare fraud detection |
| spellingShingle | John T. Hancock Richard A. Bauder Huanjing Wang Taghi M. Khoshgoftaar Explainable machine learning models for Medicare fraud detection Journal of Big Data Big Data Class imbalance Explainable machine learning models Ensemble supervised feature selection Medicare fraud detection |
| title | Explainable machine learning models for Medicare fraud detection |
| title_full | Explainable machine learning models for Medicare fraud detection |
| title_fullStr | Explainable machine learning models for Medicare fraud detection |
| title_full_unstemmed | Explainable machine learning models for Medicare fraud detection |
| title_short | Explainable machine learning models for Medicare fraud detection |
| title_sort | explainable machine learning models for medicare fraud detection |
| topic | Big Data Class imbalance Explainable machine learning models Ensemble supervised feature selection Medicare fraud detection |
| url | https://doi.org/10.1186/s40537-023-00821-5 |
| work_keys_str_mv | AT johnthancock explainablemachinelearningmodelsformedicarefrauddetection AT richardabauder explainablemachinelearningmodelsformedicarefrauddetection AT huanjingwang explainablemachinelearningmodelsformedicarefrauddetection AT taghimkhoshgoftaar explainablemachinelearningmodelsformedicarefrauddetection |