Academic Journal of Computing & Information Science, 2024, 7(9); doi: 10.25236/AJCIS.2024.070904.
Yiye Zheng1, Linze Li2, Bin Gao3, Hansheng Yang4, Jiaqi Jiang5
1Artificial Intelligence Institute, Yango University, Fuzhou, Fujian, 351100, China
2School of Physics and Astronomy, Sun Yat-sen University, Zhuhai, Guangdong, 519000, China
3Wuxi Kuangyuan Billingual School, Wuxi, Jiangsu, 214000, China
4Teensen Genesis School, Nanchang, Jiangxi, 330103, China
5The High School Attached to JXNU, Nanchang, Jiangxi, 330038, China
While the insurance industry is growing quickly, it is also facing a growing fraud problem, which poses a threat to the operations and stability of insurance companies. This article proposes a machine learning-based approach aimed at identifying and preventing fraud in auto insurance. The method improves the accuracy through feature selection, sample equalization and model optimization. A new index is also proposed to measure the stability of the prediction algorithm. The experiment shows that compared with the existing methods, the method proposed in this paper promotes the accuracy of detecting fraud behavior, and the stability of the algorithm is improved. The proposal of this method can help to better protect the insurance companies from fraud and ensure the stable development of their business.
Insurance fraud; Machine learning; Data analysis
Yiye Zheng, Linze Li, Bin Gao, Hansheng Yang, Jiaqi Jiang. A fraud detection method based on integrated machine learning. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 9: 25-31. https://doi.org/10.25236/AJCIS.2024.070904.
[1] Bolton, R. J., & Hand, D. J. (2001). Unsupervised profiling methods for fraud detection. Credit scoring and credit control VII, 235-255.
[2] Valavan, M., & Rita, S. (2023). Predictive-Analysis-based Machine Learning Model for Fraud Detection with Boosting Classifiers. Computer Systems Science & Engineering, 45(1).
[3] Fang, Y., Zhang, Y., & Huang, C. (2019). Credit Card Fraud Detection Based on Machine Learning. Computers, Materials & Continua, 61(1).
[4] Nielsen, D. (2016). Tree boosting with xgboost-why does xgboost win" every" machine learning competition? (Master's thesis, NTNU).
[5] Ramani, K., Suneetha, I., Pushpalatha, N., & Harish, P. (2022). Gradient boosting techniques for credit card fraud detection. Journal of Algebraic Statistics, 13(3), 553-558.
[6] Yi, D., Deng, G., Dong, C., Zhu, M., Lyu, Z., & Zhu, S. (2020). Medical insurance fraud detection algorithm based on graph convolutional neural network. Journal of Computer Applications, 40(5), 1272.
[7] Tiwari, P., Mehta, S., Sakhuja, N., Kumar, J., & Singh, A. K. (2021). Credit card fraud detection using machine learning: a study. arXiv preprint arXiv:2108.10005.
[8] Esmaily, Jamal, Reza Moradinezhad, and Jamal Ghasemi. "Intrusion detection system based on multi-layer perceptron neural networks and decision tree." 2015 7th Conference on Information and Knowledge Technology (IKT). IEEE, 2015.
[9] Behera, T. K., & Panigrahi, S. (2015). Credit card fraud detection: a hybrid approach using fuzzy clustering & neural network. In 2015 second international conference on advances in computing and communication engineering, IEEE, pp. 494-499.