Intelligent and other computational techniques in insurance : theory and applications /
This book presents recent advances in the theory and implementation of intelligent and other computational techniques in the insurance industry. The paradigms covered encompass artificial neural networks and fuzzy systems, including clustering versions, optimization and resampling methods, algebraic...
Saved in:
Corporate Authors: | |
---|---|
Group Author: | ; |
Published: |
World Scientific Pub. Co.,
|
Publisher Address: | Singapore ; River Edge, N.J. : |
Publication Dates: | 2003. |
Literature type: | eBook |
Language: | English |
Series: |
Series on innovative intelligence ; v. 6 |
Subjects: | |
Online Access: |
http://www.worldscientific.com/worldscibooks/10.1142/5441#t=toc |
Summary: |
This book presents recent advances in the theory and implementation of intelligent and other computational techniques in the insurance industry. The paradigms covered encompass artificial neural networks and fuzzy systems, including clustering versions, optimization and resampling methods, algebraic and Bayesian models, decision trees and regression splines. Thus, the focus is not just on intelligent techniques, although these constitute a major component; the book also deals with other current computational paradigms that are likely to impact on the industry. The application areas include asset allocation, asset and liability management, cash-flow analysis, claim costs, classification, fraud detection, insolvency, investments, loss distributions, marketing, pricing and premiums, rate-making, retention, survival analysis, and underwriting. |
Carrier Form: | 1 online resource (xxiv,664pages) : illustrations. |
Bibliography: | Includes bibliographical references and index. |
ISBN: | 9789812794246 (electronic bk.) |
CLC: | F84-37 |
Contents: |
ch. 1. Insurance applications of neural networks, fuzzy logic, and genetic algorithms. 1. Introduction. 2. Neural network (NN) applications. 3. Fuzzy logic (FL) applications. 4. Genetic algorithm (GA) applications. 5. Comment -- ch. 2. An introduction to neural networks in insurance. 1. Introduction. 2. Background on neural networks. 3. Example 1: simple example of fitting a nonlinear function to claim severity. 4. Example 2: using neural networks to fit a complex nonlinear function. 5. Correlated variables and dimension reduction. 6. Conclusion -- ch. 3. Practical applications of neural networks in property and casualty insurance. 1. Introduction. 2. Fraud example. 3. Underwriting example. 4. Conclusions -- ch. 4. Statistical learning algorithms applied to automobile insurance ratemaking. 1. Introduction. 2. Concepts of statistical learning theory. 3. Mathematical objectives. 4. Methodology. 5. Models. 6. Experimental results. 7. Application to risk sharing pool facilities. 8. Conclusion -- ch. 5. An integrated data mining approach to premium pricing for the automobile insurance industry. 1. Introduction. 2. A data mining approach. 3. Risk classification and prediction of claim cost. 4. Prediction of retention rates and price sensitivity. 5. Determining an optimal portfolio of policy holders. 6. Conclusions -- ch. 6. Fuzzy logic techniques in the non-life insurance industry. 1. Insurance market. 2. Fuzzy logic in insurance. 3. Some extensions. 4. Classification. 5. The future of insurance -- ch. 7. Population risk management: reducing costs and managing risk in health insurance. 1. Background. 2. Identification (targeting) of high-risk populations. 3. Application of interventions and other risk management techniques. 4. Summary and conclusions -- ch. 8. A fuzzy set theoretical approach to asset and liability management and decision making. 1. Introduction. 2. Fuzzy numbers and their arithmetic operations. 3. Fuzzy immunization theory. 4. Fuzzy matching of assets and liabilities. 5. Bayesian decision method. 6. Fuzzy Bayesian decision method. 7. Decision making under fuzzy states and fuzzy alternatives. 8. Conclusions -- ch. 9. Using neural networks to predict failure in the marketplace. 1. Introduction. 2. Overview and background. 3. Neural network methods for life insurer insolvency prediction. 4. Neural network methods for property-liability insurer insolvency prediction. 5. Conclusion and further directions. ch. 10. Illustrating the explicative capabilities of Bayesian learning neural networks for auto claim fraud detection. 1. Introduction. 2. Neural networks for classification. 3. Input relevance determination. 4. Evidence framework. 5. PIP claims data. 6. Empirical evaluation. 7. Conclusion -- ch. 11. Merging soft computing technologies in insurance-related applications. 1. Introduction. 2. Advantages and disadvantages of NNs, FL and GAs. 3. NNs controlled by FL. 4. NNs generated by GAs. 5. Fuzzy inference systems (FISs) tuned by GAs. 6. FISs tuned by NNs. 7. GAs controlled by FL. 8. Neuro-fuzzy-genetic systems. 9. Conclusions -- ch. 12. Robustness in Bayesian models for bonus-malus systems. 1. Introduction. 2. The models. 3. Premium calculation in a bonus-malus system. 4. Technical results. 5. Illustrations. 6. Conclusions and further works -- ch. 13. Using logistic regression models to predict and understand why customers leave an insurance company. 1. Introduction. 2. Qualitative dependent variable models. 3. Customer information. 4. Empirical results. 5. Conclusions -- ch. 14. Using data mining for modeling insurance risk and comparison of data mining and linear modeling approaches. 1. Introduction. 2. Data mining - the new methodology for analysis of large data sets - areas of application of data mining in insurance. 3. Data mining methodologies. Decision trees (CART), MARS and hybrid models. 4. Case study 1. Predicting, at the outset of a claim, the likelihood of the claim becoming serious. 5. Case study 2. Health insurer claim cost. 6. Neural networks. 7. Conclusion -- ch. 15. Emerging applications of the resampling methods in actuarial models. 1. Introduction. 2. Modeling US mortality tables. 3. Methodology of cash-flow analysis with resampling. 4. Conclusions -- ch. 16. System intelligence and active stock trading. 1. Introduction. 2. Determination of the asset universe. 3. Implementation. 4. Model description. 5. Results. 6. Conclusions and further research -- ch. 17. Asset allocation: investment strategies for financial and insurance portfolio. 1. Introduction. 2. Single-period Markowitz model. 3. Multi-period mean-variance model. 4. A brief review of Merton's model. 5. Continuous-time VaR optimal portfolio. 6. Continuous-time CaR formulation. 7. Optimal investment strategy for insurance portfolio. 8. Conclusions -- ch. 18. The algebra of cash flows: theory and application. 1. Introduction. 2. Term structure of interest rates. 3. The cash flow polynomial ring. 4. The economic multiplication and division of cash flows. 5. The probabilistic notions of duration and convexity. 6. Convex order and immunization theory. 7. Immunization of liability cash flow products. 8. Examples. 9. Conclusions. |