• The Journal of the Korean life insurance medical association
• /
• v.18
• /
• pp.117-125
• /
• 1999

암에 의한 보험금 지급의 증가와 관련하여 1996년, 1년 동안 당사에서 암진단보험금 수혜자에 대한 고찰을 통해 다음과 같은 결과를 얻었다. 1. '96년 암진단보험금 지급은 2,720건 발생하였고, 남자 777명(28.6%), 여자 1,943명(71.4%)였다. 2. 남녀별로 40대, 30대, 50대 순으로 암진단보험금이 지급되었으며, 남자에서는 각각 38.6%, 28.8%, 24.2%였고, 여자에서는 각각 31.8%, 30.3%, 26.6%였다. 3. 남자의 경우 위장계통 암이 323명(41.6%), 여자의 경우 생식기계통 암(유방암 포함)이 968명(52.4%)으로 가장 많았다. 4. 장기별 발생률은 남자는 위(27.5%), 간(22.0%), 폐(8.1%), 여자는 유방(21.2%), 위(14.9%), 자궁경부(13.2%)순으로 나타났다. 5. 경과기간별 암진단보험금 지급 양상은 가입 후 1년 이내 25.1%, 1년에서 2년 이하 18.9%, 1년 후 55.9% 발생하였다. 6. 6개월 이내 암진단보험금은 폐암(15.0%), 갑상선암(14.5%), 자궁경암(13.6%), 유방암(13.1%) 순으로 지급되었다. 7. '96년 암진단보험금 수혜자 중 사망은 '98년 10월 현재 805건(29.6%) 발생하였고, 암종류별 사망률은 간암(76.9%), 폐암(74.0%), 위암(36.3%) 순으로 높았다.

• The Journal of the Korea Contents Association
• /
• v.10 no.8
• /
• pp.349-359
• /
• 2010

The purpose of this study is to design the On-line Insurance Sales Support System using Case-Based Reasoning(CBR). In on-line insurance subscription process, this system provides the personalized insurance payment cases and insurance statistics for customers to entice an insurance subscription. By measuring, specifically, similarities between the user profile and insurance payment cases, it suggests the best insurance payment case which has the highest similarity and reflects the latest in the insurance payment cases. In addition, it serves the insurance statistical information that matches with the attributes of the finally-selected case. These functions can be useful in on-line insurance sales.

• Communications for Statistical Applications and Methods
• /
• v.15 no.4
• /
• pp.551-562
• /
• 2008

The loss reserve is defined as a provision for an insurer's liability for claims or an insurer's estimate of the amount an individual claim will ultimately cost. For the estimation of the loss reserve, the data which make up the claims in general is represented as run-off triangle. The chain ladder method has known as the most representative one in the estimation of loss reserves based on such run-off triangular data. However, this fails to capture change point in trend. In order to test of structural changes of development factors, we will present the test statistics and procedures. A real data analysis will also be provided.

• Korean Journal of Cognitive Science
• /
• v.23 no.2
• /
• pp.205-224
• /
• 2012

How would people who buy an insurance policy respond to a low probability risk with a high future cost? Presented with a scenario describing a low probability accident of a chemical plant, participants in four experiments were asked to rate their perception of the risk and also their intention to buy an insurance of a given premium, an insurance, or a ratio insurance. Participants differently responded only to ratio insurance when rating their perception of risk, not to either premium or insurance. The pattern of results in four experiments converged to the conclusion that ratio insurance, an ecologically valid cue, makes people sensitive to the level of risk expressed in low probabilities of an accident. Our results were consistent with the prediction generated by the ecological cue hypothesis which empathizes the importance of frequency over probability in risk perception (Gigerenzer, 2000).

• Journal of Digital Convergence
• /
• v.18 no.10
• /
• pp.175-180
• /
• 2020

Through case studies for insurance service marketing using artificial intelligence(AI) in the insurtech industry, it investigated how innovative technologies(artificial intelligence, machine learning etc.) are being used in the insurance ecosystems. In particular, through domestic and international case studies, it was examined by Lemonade's service of insurance contracts and getting the indemnity and AI company's service of calculating the compensation through a medical certificate image based on OCR, which brought disruptive innovations using artificial intelligence. As a result of the case analysis, these services have drastically shortened the lead time of insurance contracts and payment through machine learning using numerous customer data based on artificial intelligence. And accurate and reasonable compensation was calculated in the estimation of indemnity, which has a lot of disputes between customers and insurance companies. It was able to increase customer satisfaction and customer value.

• The Korean Journal of Applied Statistics
• /
• v.25 no.1
• /
• pp.81-87
• /
• 2012

A continuous time risk model is considered, where the premium rate is constant and the claims form a compound Poisson process. We assume that an injection is made, which is an immediate increase of the surplus up to level u > 0 (initial level), when the level of the surplus goes below ${\tau}$(0 < ${\tau}$ < u). We derive the formula of the ruin probability of the surplus by establishing an integro-differential equation and show that an explicit formula for the ruin probability can be obtained when the amounts of claims independently follow an exponential distribution.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.3 no.4
• /
• pp.325-332
• /
• 2002

In the process of designing pareto optimal insurance contract, it is necessary to assume that insurance contract conditions are endogenous to build a model. The expected utility, the non-expected utility and the state-dependent utility function can be applied as a insurance decision making principle. The insurance costs may have the linear, convex, and concave ralationship with the indemnity schedule. However, the sunk cost and fixed cost must be recognized. The deductible which decides whether an insurance contract to be a full or partial insurance contract can exist in the forms of straight deductible or diminishing deductible. Indeciding the level of deductible, the types of the insurance and the risks to be insured should be the deciding factors. Especially for recall insurance, there is relatively high chance that the recalling company being bankrupt. Therefore, the possibility of bankrupcy should be the considering factor in deciding the policy limit. The existence of the incomplete market and uninsurable background risk should be understood as restricting conditions of the pareto-optimal insurance contract.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.221-228
• /
• 2024

Predicting insurance claims is a key task for insurance companies to manage risks and maintain financial stability. Accurate insurance claim predictions enable insurers to set appropriate premiums, reduce unexpected losses, and improve the quality of customer service. This study aims to enhance the performance of insurance claim prediction models by applying ensemble learning techniques. The predictive performance of models such as Random Forest, Gradient Boosting Machine (GBM), XGBoost, Stacking, and the proposed Dynamic Weighted Ensemble (DWE) model were compared and analyzed. Model performance was evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), and the Coefficient of Determination (R²). Experimental results showed that the DWE model outperformed others in terms of evaluation metrics, achieving optimal predictive performance by combining the prediction results of Random Forest, XGBoost, LR, and LightGBM. This study demonstrates that ensemble learning techniques are effective in improving the accuracy of insurance claim predictions and suggests the potential utilization of AI-based predictive models in the insurance industry.

• 방재와보험
• /
• s.92
• /
• pp.25-29
• /
• 2002

• The Korean Journal of Applied Statistics
• /
• v.22 no.5
• /
• pp.937-942
• /
• 2009

In this paper, a continuous-time risk process in an insurance business is considered, where the premium rate is constant and the claim process forms a compound Poisson process. We say that a ruin occurs if the surplus of the risk process becomes negative. It is practically impossible to calculate analytically the ruin probability because the theoretical formula of the ruin probability contains the recursive convolutions and infinite sum. Hence, many authors have suggested approximation formulas of the ruin probability. We introduce a new approximation formula of the ruin probability which extends the well-known De Vylder's and exponential approximation formulas. We compare our approximation formula with the existing ones and show numerically that our approximation formula gives closer values to the true ruin probability in most cases.