• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.103-104
• /
• 2017

최근들어 보험사기로 인한 피해가 날로 극심해지고 있다. 이러한 보험사기로 인한 피해를 예방하고 억제하기 위해 오랜시간 논의를 해왔으며, 결국 보험사기방지 특별법을 제정하여 2016. 9. 30. 시행하였다. 그러나 단지 이러한 특별법 시행만으로는 보험사기로 인한 폐해를 완전히 해결할 수 없다. 따라서 특별법 시행으로 인한 현실적인 보험사기 억제효과를 살펴보고 이에 대한 문제점을 분석하여야 한다. 이에 본 연구에서는 보험사기방지 특별법 시행으로 인한 효과에 대하여 현실적으로 살펴보고, 이에 대한 문제점을 모색한 후 개선방안을 제시해 보고자 한다.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.117-127
• /
• 2020

Recently, proving insurance fraud has become increasingly difficult because it occurs intentionally and secretly via organized and intelligent conspiracy by specialists such as medical personnel, maintenance companies, insurance planners, and insurance subscribers. In the case of car accidents, it is difficult to prove intentions; in particular, an insurance company with no investigation rights has practical limitations in proving the suspicions. This paper aims reveal that the detection of organized and conspired insurance fraud, which had previously been difficult, could be dramatically improved through conspiring insurance fraud detection modeling using social network analysis and visualization of the relation between suspected group entities and by seeking developmental research possibilities of data analysis techniques.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.212-215
• /
• 2018

현재 자동차 사고 보험에서는 보험사기 문제가 해결되지 못하고 있다. 매년 자동차 보험 회사의 보험사기로 인한 금전적 손해는 증가하고 있다. 또한 보험사기를 막기 위해 적용되는 필수적인 보험 회사 직원의 현장 방문은 비효율적이고 보험금을 받을 때까지 많은 시간을 소모한다. 이를 해결하기 위해 자동차 보험에 블록체인을 적용한 go2solution은 기존 보험 처리 과정을 단축시켰지만 보험청구자의 사진만으로 사고 발생을 판단하기 때문에 사고를 입증하는데 증거가 부족하고 이를 이용한 보험 사기가 가능하다. 따라서 사고 발생 여부의 신뢰도를 측정하여 보험사기를 방지할 수 있도록 블록체인 기반 자동차 보험 신뢰모델을 제안한다. 포그 컴퓨팅을 적용하여 차량, 보험회사, RSU의 정보 공유를 원활하게 한다. 또한 목격자들이 신뢰요소로 적용될 수 있도록 블록체인 컨소시엄을 통한 인센티브 시스템을 적용하여 목격자들은 적극적으로 사고정보를 제공한다. 이렇게 수집된 다양한 신뢰요소 데이터를 분석하여 신뢰점수와 등급을 정한다. 이때 회귀분석을 적용하여 각각의 신뢰요소의 중요도에 따라 다른 가중치를 적용하여 정확한 신뢰점수를 책정한다. 결과적으로 보험회사는 보험사기 피해액을 절감하고 보험청구자는 인센티브를 사용하여 적은 보험료를 지불한다.

• The Korean Journal of Financial Management
• /
• v.23 no.1
• /
• pp.227-242
• /
• 2006

This paper analyzes insurance crimes using a game theoretic model. In blackmailing cases involving automobile accidents, insurance criminals deliberately induce innocent drivers(victims) to commit a moving violation such as crossing over the center dividing yellow line, and collide with the victims. After the collision, the criminals and the victims effectively engage in a bargaining game over the amount of the settlement for the damage. Because the penalty for that kind of moving violation is very severe (even criminally prosecuted), the victims do not have much bargaining power. Exploiting the weak bargaining power of the victims, the criminals demand and receive huge compensation (including settlement) from the victims. In the model, it is shown that under the current law agents have perverse incentives leading to insurance crimes. The criminals have incentive to induce car collisions and extract huge settlement from the victims. Based on the analysis, it is suggested that lowering the severity of penalty for certain kind of violation may be needed to prevent insurance crimes, in addition to increasing the crime investigation activities and strengthening punishment for insurance criminals.

• Information Systems Review
• /
• v.5 no.1
• /
• pp.49-60
• /
• 2003

The purpose of this study is to empirically and practically verify the applicability of visualization data mining tool in detecting real-word insurance frauds that are now emerged as one of the most serious problems socially and economically. For the verification, Analyst's Notebook by i2, which has been known as the most effective visualization data mining tool, was adopted. With Analyst's Notebook, fraud-probable insurance transactions from a very large insurance claims are selected and then substantiation for insurance frauds are attempted. The results show that Analyst's Notebook not only detects insurance fraud transactions from a vast number of insurance claims, but is also able to pinpoint organized crime group by associating one fraud transaction to another fraud transaction. Therefore, it is safe to conclude that visualization data mining is very effective in detecting false transactions and crime behaviors including insurance fraud.

• Journal of Digital Convergence
• /
• v.20 no.2
• /
• pp.241-250
• /
• 2022

Due to the COVID-19 pandemic, with increased 'untact' services and with unstable household economy, the bike insurance fraud is expected to surge. Moreover, the fraud methodology gets complicated. However, the fraud detection model for bike insurance is absent. we deal with the issue of skewed class distribution and reflect the criterion of fraud detection expert. We utilize a balanced random-forest algorithm to develop an efficient bike insurance fraud detection model. As a result, while the predictive performance of balanced random-forest model is superior than it of non-balanced model. There is no significant difference between the variables used by the experts and the confirmatory models. The important variables to detect frauds are turned out to be age and gender of driver, correspondence between insured and driver, the amount of self-repairing claim, and the amount of bodily injury liability.

• 방재와보험
• /
• s.121
• /
• pp.56-58
• /
• 2007

최근 경제적 이익을 목적으로, 보험에 가입된 주택이나 건물 등에 고의로 화재를 내는 보험사기성 방화가 증가하고 있다. 보험업의 건전한 발전을 위하여 손해사정 조사과정에서 밝혀진 보험사기성 방화사례에 대해 알아보자.

• Journal of Convergence for Information Technology
• /
• v.11 no.6
• /
• pp.270-281
• /
• 2021

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.

• 방재와보험
• /
• s.132
• /
• pp.17-21
• /
• 2009

• 방재와보험
• /
• s.106
• /
• pp.22-26
• /
• 2005