Special Issue "Claim Models: Granular Forms and Machine Learning Forms"

A special issue of Risks (ISSN 2227-9091).

Deadline for manuscript submissions: 31 August 2019

Special Issue Editor

Guest Editor
Prof. Greg Taylor

School of Risk & Actuarial, University of New South Wales
Website | E-Mail
Interests: Insurance loss reserving; Stochastic dependence

Special Issue Information

Dear Colleagues,

For many years, much claim modelling has been performed on aggregate data, such as triangles, using supervised models with highly structure algebraic forms. The increased computing capability of more recent years has enabled some tentative advances beyond this frontier. Modelling appears to have developed in two directions that, while currently generating distinct literature streams, are not necessarily disjoint. These are:

  • Granular models (GMs), including individual claim models;
  • Machine learning models (MLMs), including regularized regression, neural nets, gradient boosting machines, etc.

Each of these model types brings with it its own advantages and disadvantages. For example, GMs usually endeavor to model the claim process in some degree of detail. This can introduce numerous cascaded sub-models, and many difficult questions of dependencies between model components. The building of such models can be extremely labour-intensive.

On the other hand, MLMs can often cut through these difficulties, and some can operate in an unsupervised environment. The price to be paid for this, however, is a loss of model interpretability. Many MLMs can be highly opaque, with no apparent physical meaning.

The purpose of the Special Edition is to advance the application of both GMs and MLMs to claim modelling, but with particular interest in models that bridge the gap between these two types. This might include, for example, the use of semi-structured MLMs, such as:

  • the use of explainable neural nets, i.e. those whose output is confined to a prescribed family of algebraic forms; or
  • structured GMs whose parameters and internal dependencies are estimated by machine learning.

Prof. Greg Taylor
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Risks is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 350 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • granular models
  • machine learning
  • neural net
  • supervised modelling
  • unsupervised modelling

Published Papers

This special issue is now open for submission.
Risks EISSN 2227-9091 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top