Natural language interactions enhanced by data visualization to explore insurance claims and manage risk

Md Rafiqul ISLAM, Imran RAZZAK, Xianzhi WANG, Peter TILOCCA, Guandong XU

Research output: Contribution to journalArticlespeer-review

3 Citations (Scopus)

Abstract

Claims analysis and risk management is key to avoiding fraud and managing risk in the life insurance industry. Though visualization plays a fundamental role in supporting analysis tasks in the business domain, exploring user behaviour remains a challenging task. The prevalence of natural language interactions enhanced with data visualization has become quite the norm. With the increasing demand for visualization tools and varying levels of user expertise, the use of a natural language interface (NLI) is common. However, the design of visual analytics tools enhanced by NLIs for risk management and claim analysis requires thorough task analysis and domain expertise. In this work, we investigate an alternative approach through a natural language interaction-based interactive visualization such as a chart, pie chart, or histogram, which can be used for insurance claim analysis and risk management. We design a new visual analytics solution named InsCRMVis which is enhanced by NLIs. We present an expert evaluation of InsCRMVis based on the Task Load Index questionnaire which is currently the standard metrics measure to investigate its usability (effectiveness, efficiency, satisfaction) to support human task performance. To evaluate its performance, we performed a user study of ten experts which suggests that InsCRMVis can provide better insights and assistance to insurance managers in reducing loss and guiding changes to insurance premium policies. Furthermore, we provide a concise set of guidelines that can be used when visualizing risk to avoid dangers in the insurance domain. We discuss the challenges associated with the use of a visualization system in the insurance industry, focusing on aspects related to visualization research. Copyright © The Author(s).

Original languageEnglish
JournalAnnals of Operations Research
Early online dateJan 2022
DOIs
Publication statusE-pub ahead of print - Jan 2022

Citation

ISLAM, M. R., Razzak, I., Wang, X., Tilocca, P., Xu, G. (2022). Natural language interactions enhanced by data visualization to explore insurance claims and manage risk. Annals of Operations Research. Advance online publication. https://doi.org/10.1007/s10479-021-04465-7

Keywords

  • User interface design
  • Natural language interfaces
  • Risk management

Fingerprint

Dive into the research topics of 'Natural language interactions enhanced by data visualization to explore insurance claims and manage risk'. Together they form a unique fingerprint.