AutoReserve: A Web-Based Tool for Personal Auto Insurance Loss Reserving with Classical and Machine Learning Methods

Lu Xiong (), Vajira Manathunga, Jiyao Luo, Nicholas Dennison, Ruicheng Zhang and Zhenhai Xiang
Additional contact information
Lu Xiong: Department of Mathematical Sciences, College of Basic and Applied Sciences, Middle Tennessee State University, Murfreesboro, TN 37132, USA
Vajira Manathunga: Department of Mathematical Sciences, College of Basic and Applied Sciences, Middle Tennessee State University, Murfreesboro, TN 37132, USA
Jiyao Luo: Department of Mathematical Sciences, College of Basic and Applied Sciences, Middle Tennessee State University, Murfreesboro, TN 37132, USA
Nicholas Dennison: Department of Mathematical Sciences, College of Basic and Applied Sciences, Middle Tennessee State University, Murfreesboro, TN 37132, USA
Ruicheng Zhang: Department of Mathematical Sciences, College of Basic and Applied Sciences, Middle Tennessee State University, Murfreesboro, TN 37132, USA
Zhenhai Xiang: Department of Mathematical Sciences, College of Basic and Applied Sciences, Middle Tennessee State University, Murfreesboro, TN 37132, USA

Risks, 2023, vol. 11, issue 7, 1-17

Abstract: In this paper, we developed a Shiny-based application called AutoReserve. This application serves as a tool used for a variety of types of loss reserving. The primary target audience of the app is personal auto actuaries, who are professionals in the insurance industry specializing in assessing risks and determining insurance premiums for personal vehicles. However, the app is not limited exclusively to actuaries. Other individuals or entities, such as insurance companies, researchers, or analysts, who have access to the necessary data and require insights or analysis related to personal auto insurance, can also benefit from using the app. It is the first web-based application of its kind that is free to use and deployable from the personal computer or mobile device. AutoReserve is a software solution that caters to the needs of insurance professionals where only a few existing web-based applications are available. The application is divided into three parts: a summary of the loss data, a classical loss reserving tool, and a machine learning loss reserving tool. Each component of the application functions differently and allows for inputs from the user to analyze the provided loss data. The user, in other words, individuals or entities who utilize the Auto Reserve application, can then use the outputs for these three sections to improve his or her risk management or loss reserving process. AutoReserve is unique compared to other loss reserving tools because of its ability to employ both traditional, spreadsheet-based and modern, machine-learning-based loss reserving tools. AutoReserve is accessible on the web. The app is currently usable and is still undergoing frequent updates with new features and bug fixes.

Keywords: property and casualty insurance; insurance data analytics; loss reserving; machine learning; R shiny; data visualization (search for similar items in EconPapers)
JEL-codes: C G0 G1 G2 G3 K2 M2 M4 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-9091/11/7/131/pdf (application/pdf)
https://www.mdpi.com/2227-9091/11/7/131/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jrisks:v:11:y:2023:i:7:p:131-:d:1194165

Access Statistics for this article

Risks is currently edited by Mr. Claude Zhang

More articles in Risks from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().