International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Healthcare Fraud Detection Using XGBoost |
|---|---|
| ABSTRACT | Healthcare fraud has emerged as a critical financial and ethical challenge within the global medical insurance ecosystem, resulting in substantial economic losses and compromised service quality. Fraudulent practices such as false claims, exaggerated billing, and misuse of insurance policies not only burden insurance providers but also negatively impact genuine patients. In this context, the need for an intelligent, automated, and scalable fraud detection system has become increasingly essential.This project proposes a robust web-based Healthcare Fraud Detection System that leverages the capabilities of the XGBoost (Extreme Gradient Boosting) machine learning algorithm to accurately classify healthcare companies as fraudulent or genuine. The dataset used for training consists of 500 labeled healthcare company records, enabling the model to learn distinguishing features between fraudulent and legitimate entities.Experimental evaluation demonstrates that the XGBoost model achieves a high level of performance, with an accuracy of 94.2%, precision of 91.8%, recall of 93.5%, and an F1-score of 92.6%. These results highlight the effectiveness of the model in handling classification tasks with imbalanced and complex datasets.The developed web application provides a user-friendly interface where authenticated users can input a healthcare company name and instantly obtain a prediction result. The output is visually represented as FRAUD (highlighted in red) or NOT FRAUD (highlighted in green), along with detailed company-related information such as disease type and insurance category. This real-time prediction capability enhances decision-making and reduces dependency on manual verification processes.Overall, the proposed system demonstrates a scalable and efficient approach for healthcare fraud detection, combining machine learning techniques with web-based deployment to deliver practical and real-world applicability. |
| AUTHOR | ANAGHA P P, SREETHA S, PRAVEENA S, K ABINAYA Department of Artificial Intelligence and Data Science, Christ The King Engineering College, Karamadai, Coimbatore, Tamil Nadu, India Assistant Professor, Department of Artificial Intelligence and Data Science, Christ The King Engineering College, Karamadai, Coimbatore, Tamil Nadu, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405031 |
| pdf/31_Healthcare Fraud Detection Using XGBoost.pdf | |
| KEYWORDS | |
| References | 1. Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. 2. Joudaki, H., et al. Using Data Mining to Detect Healthcare Fraud. 3. Pedregosa, F., et al. Scikit-learn: Machine Learning in Python. 4. Flask Official Documentation. 5. IEEE Xplore Digital Library. |
