Education, Science, Technology, Innovation and Life
Open Access
Sign In

Research on medical insurance fraud identification method based on multi-source datasets

Download as PDF

DOI: 10.23977/jeis.2024.090307 | Downloads: 14 | Views: 458

Author(s)

Jinhong Zhang 1

Affiliation(s)

1 School of Economics and Management, Jinzhong College of Information, Jinzhong, Shanxi, 030800, China

Corresponding Author

Jinhong Zhang

ABSTRACT

Due to the fact that datasets pertaining to health insurance are typically stored in different departments and involve multiple databases, conventional data analysis and traditional fraud research methods often fall short in accurately identifying fraudulent activities. To address this challenge, this paper, on one hand, starts by recognizing the unique characteristics of various collected datasets. It employs a multi-source data fusion approach, initially combining their features. Subsequently, an exploratory data analysis is conducted on the fused dataset. Compared to previous single datasets, the merged dataset contains more features, significantly enhancing the model's fitting performance. This approach maximizes the utilization of information within the data, allowing for better exploitation of the data's potential.On the other hand, this paper integrates the strategy of active learning with traditional logistic regression methods, constructing a novel model. The model is initially trained on labeled datasets, and after multiple experiments, it was observed that the fitting accuracy of the active learning model, constructed using the BT strategy (a type of active learning sample extraction strategy), surpassed that of a standalone logistic regression model. This innovative approach provides a new avenue for improving the accuracy of health insurance fraud detection.

KEYWORDS

Insurance fraud; Active learning; Logistic Regression

CITE THIS PAPER

Jinhong Zhang, Research on medical insurance fraud identification method based on multi-source datasets. Journal of Electronics and Information Science (2024) Vol. 9: 41-47. DOI: http://dx.doi.org/10.23977/10.23977/jeis.2024.090307.

REFERENCES

[1] Wang S L, Pai H T, Wu M F, et al. The evaluation of trustworthiness to identify health insurance fraud in dentistry[J]. Artificial intelligence in medicine, 2017, 75: 40-50. 
[2] Thornton D. Brinkhuis M, Amrit C, et al. Categorizing and Describing the Types of Fraud in Healthcare [J]. Procedia Comput Science, 2015, 64(1): 713-720. 
[3] Faseela V S, Thangam D P. A Review on Health Insurance Claim Fraud Detection[J]. International Journal of Engineering Research Science (IJOER), 2015, (4):47-49. 
[4] Yip W, Hsiao W C. What Drove the Cycles of Chi- nese Health System Reforms[J]. Health System Re form, 2015, 1(1): 52-61. 
[5] Yu, H. Universal Health Insurance Coverage for 1. 3 Billion[J]. Health Poli- People: What Accounts for China's Successcy, 2015, 119(9): 1145-1152. 
[6] LIU J, BIER E, WILSON A, et al. Graph analysis for detecting fraud, waste, and abuse in healthcare data[C]// Proceedings of the 27th Conference on Innovative Applications of Artificial Intelli-gence. Palo Alto, CA: AAAI Press, 2015:3912-3919. 
[7] Wilhelm W K. The Fraud Management Lifecycle Theory: A Holistic Approach to Fraud Management[J]. Journal of Eco- nomic Crime Management, 2004, 2(2): 1-38. 
[8] Faseela V S, Thangam P. A Review on Health Insurance Claim Fraud Detection[J]. International Journal of Engi- neering Research Science, 2015, 1(1):47-49.  
[9] Hubick, K. T.. Artificial neural networks in Australia. Canberra: Common wealth of Australia, 1992. 
[10] Stijn Viaene, Richard A. Derrig, Guido Dedene. A Case Study of Applying Boosting Naive Bayes to Claim Fraud Diagnosis. Ieee Transaction on Knowledge and Data Engineering, 2004: Vo1. 18, NO. 5
[11] Fletcher Lu, J. Efrim Boritz. Detecting fraud in health insurance data: learning to model incomplete benford's law distributions. Lecture notes in computer science, 2005(3720):633-640. 
[12] Jing Li, Kuei-Ying Huang, Jionghua Jin, Jianjun Shi. A Survey on Statistical 51 Methods for Health Care Fraud Detection. Health Care Manage Science, 2007, (5):1-21. 
[13] James H. Bisker, Kate Ehrlich. Health Insurance Fraud Detection Using Socia Network Analytics, United States Patent Application Publication. 2008:US 2008/0172257
[14] Ekina T, Leva F, Ruggeri F, et al. Application of bayesian methods in detection of healthcare frad[J]. chemical engineering Transaction, 2013, 33-42. 
[15] Sadiq S, Tao Y, Yan Y, et al. Mining anomalies in medicare big data using patient rule inductionmethod[C]2017 IEEE third international conference on multimedia Big Data (BigMM). IEEE, 2017:185-192. 
[16] Chuishi Meng, Xiuwen Yi, Lu Su, Jing Gao, and Yu Zheng. 2017. City-wide Traffic Volume Inference with Loop Detector Data and Taxi Trajectories. In Proceedings of the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL '17). Association for Computing Machinery, New York, NY, USA, Article 1, 1–10.

Downloads: 10601
Visits: 361079

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.