Claim Models: Granular Forms and Machine Learning Forms

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

Deadline for manuscript submissions: closed (31 August 2019) | Viewed by 25351

Printed Edition Available!
A printed edition of this Special Issue is available here.

Special Issue Editor

Prof. Greg Taylor
E-Mail Website
Guest Editor
School of Risk & Actuarial, University of New South Wales, Kensington, NSW, Australia
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 submissions that pass pre-check are 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 monthly 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 1800 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 (6 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Editorial

Jump to: Research

2 pages, 232 KiB  
Editorial
Risks Special Issue on “Granular Models and Machine Learning Models”
Risks 2020, 8(1), 1; https://doi.org/10.3390/risks8010001 - 30 Dec 2019
Cited by 2 | Viewed by 1809
Abstract
It is probably fair to date loss reserving by means of claim modelling from the late 1960s [...] Full article
(This article belongs to the Special Issue Claim Models: Granular Forms and Machine Learning Forms)

Research

Jump to: Editorial

36 pages, 1096 KiB  
Article
Claim Watching and Individual Claims Reserving Using Classification and Regression Trees
Risks 2019, 7(4), 102; https://doi.org/10.3390/risks7040102 - 12 Oct 2019
Cited by 15 | Viewed by 3733
Abstract
We present an approach to individual claims reserving and claim watching in general insurance based on classification and regression trees (CART). We propose a compound model consisting of a frequency section, for the prediction of events concerning reported claims, and a severity section, [...] Read more.
We present an approach to individual claims reserving and claim watching in general insurance based on classification and regression trees (CART). We propose a compound model consisting of a frequency section, for the prediction of events concerning reported claims, and a severity section, for the prediction of paid and reserved amounts. The formal structure of the model is based on a set of probabilistic assumptions which allow the provision of sound statistical meaning to the results provided by the CART algorithms. The multiperiod predictions required for claims reserving estimations are obtained by compounding one-period predictions through a simulation procedure. The resulting dynamic model allows the joint modeling of the case reserves, which usually yields useful predictive information. The model also allows predictions under a double-claim regime, i.e., when two different types of compensation can be required by the same claim. Several explicit numerical examples are provided using motor insurance data. For a large claims portfolio we derive an aggregate reserve estimate obtained as the sum of individual reserve estimates and we compare the result with the classical chain-ladder estimate. Backtesting exercises are also proposed concerning event predictions and claim-reserve estimates. Full article
(This article belongs to the Special Issue Claim Models: Granular Forms and Machine Learning Forms)
Show Figures

Figure 1

12 pages, 471 KiB  
Article
DeepTriangle: A Deep Learning Approach to Loss Reserving
Risks 2019, 7(3), 97; https://doi.org/10.3390/risks7030097 - 16 Sep 2019
Cited by 25 | Viewed by 6705
Abstract
We propose a novel approach for loss reserving based on deep neural networks. The approach allows for joint modeling of paid losses and claims outstanding, and incorporation of heterogeneous inputs. We validate the models on loss reserving data across lines of business, and [...] Read more.
We propose a novel approach for loss reserving based on deep neural networks. The approach allows for joint modeling of paid losses and claims outstanding, and incorporation of heterogeneous inputs. We validate the models on loss reserving data across lines of business, and show that they improve on the predictive accuracy of existing stochastic methods. The models require minimal feature engineering and expert input, and can be automated to produce forecasts more frequently than manual workflows. Full article
(This article belongs to the Special Issue Claim Models: Granular Forms and Machine Learning Forms)
Show Figures

Figure 1

11 pages, 706 KiB  
Article
Penalising Unexplainability in Neural Networks for Predicting Payments per Claim Incurred
Risks 2019, 7(3), 95; https://doi.org/10.3390/risks7030095 - 01 Sep 2019
Cited by 2 | Viewed by 3066
Abstract
In actuarial modelling of risk pricing and loss reserving in general insurance, also known as P&C or non-life insurance, there is business value in the predictive power and automation through machine learning. However, interpretability can be critical, especially in explaining to key stakeholders [...] Read more.
In actuarial modelling of risk pricing and loss reserving in general insurance, also known as P&C or non-life insurance, there is business value in the predictive power and automation through machine learning. However, interpretability can be critical, especially in explaining to key stakeholders and regulators. We present a granular machine learning model framework to jointly predict loss development and segment risk pricing. Generalising the Payments per Claim Incurred (PPCI) loss reserving method with risk variables and residual neural networks, this combines interpretable linear and sophisticated neural network components so that the ‘unexplainable’ component can be identified and regularised with a separate penalty. The model is tested for a real-life insurance dataset, and generally outperformed PPCI on predicting ultimate loss for sufficient sample size. Full article
(This article belongs to the Special Issue Claim Models: Granular Forms and Machine Learning Forms)
Show Figures

Figure 1

18 pages, 1259 KiB  
Article
Loss Reserving Models: Granular and Machine Learning Forms
Risks 2019, 7(3), 82; https://doi.org/10.3390/risks7030082 - 19 Jul 2019
Cited by 15 | Viewed by 4592
Abstract
The purpose of this paper is to survey recent developments in granular models and machine learning models for loss reserving, and to compare the two families with a view to assessment of their potential for future development. This is best understood against the [...] Read more.
The purpose of this paper is to survey recent developments in granular models and machine learning models for loss reserving, and to compare the two families with a view to assessment of their potential for future development. This is best understood against the context of the evolution of these models from their predecessors, and the early sections recount relevant archaeological vignettes from the history of loss reserving. However, the larger part of the paper is concerned with the granular models and machine learning models. Their relative merits are discussed, as are the factors governing the choice between them and the older, more primitive models. Concluding sections briefly consider the possible further development of these models in the future. Full article
(This article belongs to the Special Issue Claim Models: Granular Forms and Machine Learning Forms)
Show Figures

Figure 1

18 pages, 557 KiB  
Article
Individual Loss Reserving Using a Gradient Boosting-Based Approach
Risks 2019, 7(3), 79; https://doi.org/10.3390/risks7030079 - 12 Jul 2019
Cited by 18 | Viewed by 4795
Abstract
In this paper, we propose models for non-life loss reserving combining traditional approaches such as Mack’s or generalized linear models and gradient boosting algorithm in an individual framework. These claim-level models use information about each of the payments made for each of the [...] Read more.
In this paper, we propose models for non-life loss reserving combining traditional approaches such as Mack’s or generalized linear models and gradient boosting algorithm in an individual framework. These claim-level models use information about each of the payments made for each of the claims in the portfolio, as well as characteristics of the insured. We provide an example based on a detailed dataset from a property and casualty insurance company. We contrast some traditional aggregate techniques, at the portfolio-level, with our individual-level approach and we discuss some points related to practical applications. Full article
(This article belongs to the Special Issue Claim Models: Granular Forms and Machine Learning Forms)
Show Figures

Figure 1

Back to TopTop