Medicare Fraud Detection: Data Analytics Approach

Mon, Khin Yeik (2024) Medicare Fraud Detection: Data Analytics Approach. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

Healthcare fraud in Medicare costs a lot of money. Traditional methods for detecting fraud, such as rule-based systems, are often slow and inaccurate. This research explores using machine learning to detect fraud in Medicare claims. Current methods like rule-based systems have limitations. This research investigates the effectiveness of using supervised and unsupervised machine learning algorithms to identify fraudulent behavior in Medicare claims data. I propose combining three machine learning models which are Logistic Regression, Random Forest and Autoencoder for better detection. The results showed that it achieved high accuracy in detecting fraud. The random forest model was particularly skillful at capturing complex patterns in the data, while the Autoencoder successfully identified anomalies that may indicate fraud. Overall, combining these models led to a more robust fraud detection system compared to traditional methods. Combining these models creates a more reliable fraud detection system than traditional methods. This research developed machine learning models detect fraudulent behaviors in Medicare claims with high accuracy. Future research could focus on using real-time data and more advanced techniques to further improve accuracy and reduce false positives.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Del Rosal, Victor UNSPECIFIED
Uncontrolled Keywords:	Machine Learning (ML); Logistic Regression (LR); Random Forest Classifier (RFC); Autoencoder
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Artificial Intelligence for Business
Depositing User:	Ciara O'Brien
Date Deposited:	02 Jul 2025 16:57
Last Modified:	02 Jul 2025 16:57
URI:	https://norma.ncirl.ie/id/eprint/7994

Actions (login required)

View Item