MDPI - Publisher of Open Access Journals

23 pages, 3755 KiB

Open AccessArticle

Machine Learning Approaches for Auto Insurance Big Data

by Mohamed Hanafy and Ruixing Ming

Risks 2021, 9(2), 42; https://doi.org/10.3390/risks9020042 - 20 Feb 2021

Cited by 68 | Viewed by 21084

The growing trend in the number and severity of auto insurance claims creates a need for new methods to efficiently handle these claims. Machine learning (ML) is one of the methods that solves this problem. As car insurers aim to improve their customer service, these companies have started adopting and applying ML to enhance the interpretation and comprehension of their data for efficiency, thus improving their customer service through a better understanding of their needs. This study considers how automotive insurance providers incorporate machinery learning in their company, and explores how ML models can apply to insurance big data. We utilize various ML methods, such as logistic regression, XGBoost, random forest, decision trees, naïve Bayes, and K-NN, to predict claim occurrence. Furthermore, we evaluate and compare these models’ performances. The results showed that RF is better than other methods with the accuracy, kappa, and AUC values of 0.8677, 0.7117, and 0.840, respectively. Full article

► Show Figures

Figure 1

12 pages, 363 KiB

Open AccessArticle

Optimal Reinsurance Under General Law-Invariant Convex Risk Measure and TVaR Premium Principle

by Mi Chen, Wenyuan Wang and Ruixing Ming

Risks 2016, 4(4), 50; https://doi.org/10.3390/risks4040050 - 16 Dec 2016

Cited by 2 | Viewed by 4048

Abstract

In this paper, we study the optimal reinsurance problem where risks of the insurer are measured by general law-invariant risk measures and premiums are calculated under the TVaR premium principle, which extends the work of the expected premium principle. Our objective is to characterize the optimal reinsurance strategy which minimizes the insurer’s risk measure of its total loss. Our calculations show that the optimal reinsurance strategy is of the multi-layer form, i.e.,

f^{*} (x) = x \land c^{*} + {(x - d^{*})}_{+}

with

c^{*}

and

d^{*}

being constants such that

0 \leq c^{*} \leq d^{*}

. Full article

(This article belongs to the Special Issue Selected Papers from the 6th Gerber-Shiu Workshop and the 3rd Modeling of Heavy-Tail Phenomena Workshop)

► Show Figures

Figure 1

Search Results (2)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI

Saved Queries

Search Filter Reset All

Years

Feature Papers

Subjects

Journals

Article Types

Countries / Regions

Search Results (2)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI