FRAUD DETECTION IN INSURANCE WITH MACHINE LEARNING MODEL
Keywords:
fraud insurance, machine learning, artificial intelligenceAbstract
The subject of this paper is the presentation of a case of using artificial intelligence to increase the client base of companies. The data used in this model is from KAGGLE. This database consists of 1000 car accidents and car insurance claims from Ohio, Illinois and Indiana from January 1, 2015 to March 1, 2015. In this paper we present three models for artificial intelligence, logistic regression, gradient boosting and random forest. The results show that the best model can predict with 81% probability whether a potential customer would remain a customer of the company. Application of this model or similar models can be found in the detection of insurance fraud at the level of the entire industry, but also fraud at the level of certain insurance companies. This model is also a great potential for detecting tax evasion, but also in all other cases where there are similar situations and data available as in the presented case.
References
Bhowmik R. (2011). Detecting auto insurance fraud by data mining techniques. Journal of Emerging Trends in Computing and Information Sciences, 2 (4), pp.1–6. [Online]. Available at: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.302.3602&rep=rep1&type=pdf [Accessed 6 July 2021].
Bhowmik R. (2011). Detecting auto insurance fraud by data mining techniques. Journal of Emerging Trends in Computing and Information Sciences, 2 (4), pp.1–6. [Online]. Available at: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.302.3602&rep=rep1&type=pdf [Accessed 6 July 2021].
Demšar, J. and Zupan, B. (2013). Orange: Data Mining Fruitful and Fun-A Historical Perspective. Informatica, 37. [Online]. Available at: http://oranga.biolab.si [Accessed 27 May 2021].
Demšar, J. et al. (2013). Orange: Data Mining Toolbox in Python Tomaž Curk Matija Polajnar Laň Zagar. Journal of Machine Learning Research, 14. [Online]. Available at: https://www.jmlr.org/papers/volume14/demsar13a/demsar13a.pdf [Accessed 27 May 2021].
Dhieb N et al. (2019). Extreme gradient boosting machine learning algorithm for safe auto insurance operations. In: IEEE International Conference on Vehicular Electronics and Safety (ICVES). 2019. pp.1–5. [Online]. Available at: doi:10.1109/ICVES.2019.8906396 [Accessed 6 July 2021].
Dhieb N et al. (2020). A secure ai-driven architecture for automated insurance systems: Fraud detection and risk measurement. IEEE Access 8, pp.58546–58558. [Online]. Available at: https://ieeexplore.ieee.org/abstract/document/9046765/ [Accessed 6 July 2021].
Dua P and Bais S. (2014). Supervised learning methods for fraud detection in healthcare insurance. In Machine learning in healthcare informatics, Springer, Berlin, Heidelberg, pp.261–285. [Online]. Available at: doi:10.1007/978-3-642-40017-9_12 [Accessed 6 July 2021].
Friedman, J. H. (1999). Stochastic Gradient Boosting. Citeseer. [Online]. Available at: https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.33.1703&rep=rep1&type=pdf [Accessed 27 May 2021].
Itri B et al. (2019). Performance comparative study of machine learning algorithms for automobile insurance fraud detection. In: Third International Conference on Intelligent Computing in Data Sciences (ICDS) . 2019. pp.1–4. [Online]. Available at: https://ieeexplore.ieee.org/abstract/document/8942277/ [Accessed 6 July 2021].
Kirlidog M and Asuk C. (2012). A fraud detection approach with data mining in health insurance. Procedia-Social and Behavioral Sciences, pp.989–994. [Online]. Available at: https://www.sciencedirect.com/science/article/pii/S1877042812036099 [Accessed 6 July 2021].
Roy R and George KT. (2017). Detecting insurance claims fraud using machine learning techniques. In: International Conference on Circuit, Power and Computing Technologies (ICCPCT). 2017. pp.1–6. [Online]. Available at: https://ieeexplore.ieee.org/abstract/document/8074258/ [Accessed 6 July 2021].
