NORMA eResearch @NCI Library

Fraudulent Healthcare Providers detection using Machine Learning Algorithms

Jambukar, Aniket (2021) Fraudulent Healthcare Providers detection using Machine Learning Algorithms. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Healthcare services are one of the basic needs of everyone in society. Frauds in healthcare not only lose the integrity of the services but also impacts everyone financially as there is a rise in insurance premiums and healthcare expenditures. NHCAA states in 2018 itself in the USA up to 10% of total healthcare expenditure was reported as fraud and the loss was estimated to be $300 billion. Upcoding in procedures and providing unnecessary services also impacts the medical history of individuals in fraud committed by healthcare providers. This research project aims to detect fraudulent healthcare providers using machine learning algorithms. A statistical approach of MANOVA and ANOVA f-test were carried to select the best features for model building. To handle highly imbalanced healthcare datasets hybrid sampling SMOTETomek technique was used. Random forest, SVM, XGBoost, and LogisticGAM supervised machine learning models were implemented, as evaluation matrix accuracy and class 1 recall were considered. From the comparison and evaluation of four models built, LogisticGAM had the highest fraud class 1 recall of 88%.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
R Medicine > Healthcare Industry
H Social Sciences > HG Finance > Insurance
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 26 Jan 2023 17:30
Last Modified: 03 Mar 2023 11:07

Actions (login required)

View Item View Item