Journal of Convergence for Information Technology (융합정보논문지)

Convergence Society for SMB (중소기업융합학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Blockchain-Based Insurance Fraud Prediction Model Using Machine Learning

기계학습을 이용한 블록체인 기반의 보험사기 예측 모델 연구

  • Lee, YongJoo (Division of Software, Chungbuk National University)
  • Received : 2021.04.29
  • Accepted : 2021.06.20
  • Published : 2021.06.28
Download PDF
⟨ Previous Next ⟩

Abstract

With the development of information technology, the size of insurance fraud is increasing rapidly every year, and the method is being organized and advanced in conspiracy. Although various forms of prediction models are being studied to predict and detect this, insurance-related information is highly sensitive, which poses a high risk of sharing and access and has many legal or technical constraints. In this paper, we propose a machine learning insurance fraud prediction model based on blockchain, one of the most popular technologies with the recent advent of the Fourth Industrial Revolution. We utilize blockchain technology to realize a safe and trusted insurance information sharing system, apply the theory of social relationship analysis for more efficient and accurate fraud prediction, and propose machine learning fraud prediction patterns in four stages. Claims with high probability of fraud have the effect of being detected at a higher prediction rate at an earlier stage, and claims with low probability are applied differentially for post-reference management. The core mechanism of the proposed model has been verified by constructing an Ethereum local network, requiring more sophisticated performance evaluations in the future.

정보기술의 발달로 보험사기의 규모는 매년 급증하고 있고, 그 방법도 공모 형태로 조직화되고 고도화되고 있다. 이를 예측하고 검출하기 위한 다양한 형태의 예측모델이 연구되고 있지만 보험관련 정보는 매우 민감하여 공유와 접근에 위험이 높고 법적인 혹은 기술적인 제약이 많다. 이 논문에서는 최근 4차 산업 혁명의 등장으로 가장 각광받는 기술 중 하나인 블록체인을 기반으로 한 기계학습 보험사기 예측모델을 제안한다. 블록체인 기술을 활용하여 안전하고 신뢰받는 보험청구 정보 공유시스템을 실현하고, 보다 효율적이고 정확한 사기예측을 위하여 사회관계분석이론을 적용하여 각 관계에 가중치를 부여하고 기계학습 사기 예측패턴을 4단계로 나누어 제안하였다. 사기 가능성이 높은 보험청구건은 보다 앞선 단계에서 높은 예측 율로 검출되는 효과를 가지며 가능성이 낮은 청구 건은 사후에 참고하여 관리할 수 있도록 차등 적용하였다. 제안하는 모델의 중요 매커니즘은 이더리움(Ethereum) 로컬 네트워크를 구성하여 검증 하였고, 향후 보다 정교한 성능평가가 요구된다.

Keywords

Acknowledgement

This work was supported by Institute for information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIT) (No. 2019-0-00708, Integrated Development Environment for Autonomic IoT Applications based on Neuromorphic Architecture).

References

  1. Y. David. (2017). Corporate governance and blockchains. Review of Finance, 21(1), 7-31. DOI : 10.1093/rof/rfw074
  2. S. S. Jeong. (2018). Fintech Market Recent Trends and Implications. Information Technology Promotion Center(Online). http://www.itfind.
  3. D. H. Park & D. J. Ryu. (2019). Information asymmetry in insurance market through blockchain technology: Focusing on the sharing of medical information and the prevention of insurance fraud. Journal of the korean securities society, 48(4), 417-447. DOI : 10.26845/KJFS.2019.08.48.4.417
  4. Y. H. Kim & K. J. Jang. (2021). Comparative analysis of predictive performance of ultrafine dust(PM2.5) based on deep learning algorithm, Convergence Society for SMB, 11(3), 7-13.
  5. Y. S. Jeong & J. I. Im. (2019). An Anomalous Intelligence(AI) detection Model Study of Telecommunications Finalcial Fraud Incidents, KIISC, 29(1), 149-164.
  6. K. D. Kim. (2017). The impact of blockchain technology on the insurance industry. KIRI Report (Focus), 425, 2-9.
  7. M. A. Lee. (2017). Health Insurance Fraud Detection Using Data Mining Techniques. Diss. Graduate School of Seoul National University, Seoul.
  8. X. Rui & D. Wunsch. (2005). Survey of clustering algorithms. IEEE Transactions on neural networks 16(3), 645-678. DOI : 10.1109/TNN.2005.845141
  9. C. Corinna & V. Vapnik. (1995). Support-vector networks. Machine learning, 20(3), 273-297. DOI : 10.1007/BF00994018
  10. P. Yi et al. (2006). Application of clustering methods to health insurance fraud detection. In 2006 International Conference on Service Systems and Service Management (Vol. 1, pp. 116-120). IEEE. DOI : 10.1109/ICSSSM.2006.320598
  11. P. Yi et al. (2007). Application of classification methods to individual disability income insurance fraud detection. In International Conference on Computational Science (pp. 852-858). Springer, Berlin, Heidelberg.
  12. Y. S. Ko & H. S. Choi. (2017). Application and the business paradigm Changes and How to use them. Korean Society of Science and Arts Convergence, 27, 13-29. https://doi.org/10.17548/ksaf.2017.01.27.13
  13. J. Y. Ko & S. J. Bae. (2019). A Study on the Detection Method of Blockchain Abnormalities Based on Oversampling Extraction. KIIE, 45(6), 539-546.
  14. K. J. Jang. (2017). A study on Innovative Financial Services of Business Models using Blockchain Technology. e-Business, 18(6), 113-130.
  15. J. H. Jin & K. J. Ko. (2018). Blockchain technology trends and direction of utilization of health and welfare information statistics. Health and Welfare Forum, 2018(4), 96-106.
  16. G. S. Jeong. (2017). Special Report: blockchain-based insurance service trends. Seongnam : TTA.
  17. A. R. Bologa et al. (2013). Big data and specific analysis methods for insurance fraud detection. Database Systems Journal, 4(4), 30-39.
  18. K. Nian et al. (2016). Auto insurance fraud detection using unsupervised spectral ranking for anomaly. The Journal of Finance and Data Science, 2(1), 58-75. DOI : 10.1016/j.jfds.2016.03.001
  19. J. Schiller. (2006). The impact of insurance fraud detection systems. Journal of Risk and Insurance 73(3), 421-438. DOI : 10.1111/j.1539-6975.2006.00182.x
  20. J. S. Choi & J. K. Park. (2017). A Study on Blockchain-based Decentralized Internet of Things Paltform. KIISC, 27(6), 5-14.
  21. D. Y. Lee et al. (2017). Key Blockchain Technologies and Trends at Home and abroad. Communications of the Korean Institute of Information Scientists and Engineers, 35(6), 22-28.
  22. Y. J. Shin. (2021). The Improvement Plan for Personal Information Protection for Artificial Intelligence (AI) Service in South Korea. Journal of Convergence for Information Technology, 11(3), 20-33. DOI : 10.22156/CS4SMB.2021.11.03.020
  23. Y. S. Jeong et al. (2019). A Blockchain-based IIoT Information Collection Model for Improving the Productivity of Small and Medium Businesses. Journal of Convergence for Information Technology, 9(12), 1-7. DOI : 10.22156/CS4SMB.2019.9.12.001
  24. X. Zheng, Y. Le, A. P. Chan, Y. Hu & Y. Li. (2016). Review of the application of social network analysis (SNA) in construction project management research. International journal of project management, 34(7), 1214-1225. DOI : 10.1016/j.ijproman.2016.06.005
  25. M. K. Nasution. (2016). Social network mining (SNM): A definition of relation between the resources and SNA. International Journal on Advanced Science, Engineering and Information Technology, 6(6), 975-981. https://doi.org/10.18517/ijaseit.6.6.1390
  26. J. Jianqiu et al. (2013). Min-max hash for jaccard similarity. In 2013 IEEE 13th International Conference on Data Mining (pp. 301-309). IEEE. DOI : 10.1109/ICDM.2013.119