Arnold F. Shapiro

The merging of neural networks, fuzzy logic, and genetic algorithms

Abstract During the last decade, there has been increased use of neural networks (NNs), fuzzy logic (FL) and genetic algorithms (GAs) in insurance-related applications. However, the focus often has been on a single technology heuristically adapted to a problem. While this approach has been productive, it may have been sub-optimal, in the sense that studies may have been constrained by the limitations of the technology and opportunities may have been missed to take advantage of the synergies between the technologies. For example, while NNs have the positive attributes of adaptation and learning, they have the negative attribute of a “black box” syndrome. By the same token, FL has the advantage of approximate reasoning but the disadvantage that it lacks an effective learning capability. Merging these technologies provides an opportunity to capitalize on their strengths and compensate for their shortcomings. This article presents an overview of the merging of NNs, FL and GAs. The topics addressed include the advantages and disadvantages of each technology, the potential merging options, and the explicit nature of the merging.

A Hitchhiker's guide to the techniques of adaptive nonlinear models

Abstract Adaptive nonlinear models (ANMs) are currently being proposed for use in actuarial and financial modeling. The techniques of these models included such things as neural networks and genetic algorithms. While there is a general awareness of the nature of these ANM techniques, there is often only vague familiarity with the details of how these techniques are implemented. This article is intended to help alleviate this situation. Its purpose is to present an overview of ANM techniques, which includes an explanation of what they are, how they work, and a description of their key features.

An Overview of Insurance Uses of Fuzzy Logic

It has been twenty-five years since DeWit(1982) first applied fuzzy logic (FL) to insurance. That article sought to quantify the fuzziness in underwriting. Since then, the universe of discourse has expanded considerably and now also includes FL applications involving classification, projected liabilities, future and present values, pricing, asset allocations and cash flows, and investments. This article presents an overview of these studies. The two specific purposes of the article are to document the FL technologies have been employed in insurance-related areas and to review the FL applications so as to document the unique characteristics of insurance as an application area.

Implementing adaptive nonlinear models

Abstract This paper addresses that class of complex problems where there is little or no underlying theory upon which to build a model and the situation dictates the use of an adaptive approach based on the observed data. The field of study is known as adaptive nonlinear models (ANMs), and its goal is to quantify interaction terms without imposing assumptions on the solution. The purpose of this paper is to discuss, in conceptual rather than technical terms, the issues related to the implementation of these ANMs. The topics covered include: a short overview of technologies used in adaptive nonlinear modeling; modeling considerations; the model development process; and a comparison of linear and nonlinear models.

Applications of Operations-Research Techniques in Insurance

A literature review was conducted as part of a study of applications of operations-research techniques in insurance. This paper provides a cursory overview of some of the literature reviewed.

The parameters of a multiple criteria model of actuarial assumptions for pension plan valuations

Abstract Most defined benefit pension plans require a periodic actuarial valuation, so valuations are a very common procedure. Nonetheless, many of the criteria underlying the assumptions of a valuation are only vaguely defined or not defined at all. The purpose of this paper is to set the stage for resolving this problem. This is done by documenting and describing major criteria underlying the choice of actuarial assumptions for pension plan valuations and pinpointing some of the unresolved issues related thereto.

Death and survival in employee populations

Abstract This article discusses a Bayesian approach to death and survival in employee populations. First, a naive life insurance model is considered which exemplifies the basic principles involved. Next, a somewhat more complicated model is discussed which deals with the projectted cost of retirement benefits. The article ends with a comment regarding areas for future research.

THE STOCHASTIC NATURE OF PENSION COSTS

Given that expected pension costs are used as a basis for funding a pension plan, two questions immediately arise. First, what is the probability that the expected cost will be at least as great as the actual cost? Second, given that the probability of this occurrance is not satisfactory, what additional funds are required to bring the probability to a satisfactory level? An approach to these two problems is discussed in this paper.

Insurance Applications of Soft Computing Technologies

The purposes of the article are twofold: first, to review soft computing (SC) applications in insurance so as to document the unique characteristics of insurance as an application area; and second, to document the extent to which hybrid SC technologies have been employed. While it is clear that SC has made inroads into many facets of the business, in most instances the applications did not capitalized on the synergies between the SC technologies and, as a consequence, there are opportunities to extend the studies.

Quantitative Models of Pension Costs

There is considerable model building currently taking place in the pension area. In order to reduce duplication of effort and to minimize redundancy, it is important that researchers be familiar with past contributions to the pension literature. The purpose of this article is to aid researchers in this regard, by providing an overview of some of the notable contributions to the quantitative models of pension cost.