Cost-sensitive parallel learning framework for insurance intelligence operation

Xinxin Jiang, Shirui Pan, Guodong Long, Fei Xiong, Jing Jiang, Chengqi Zhang

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Recent advancements in artificial intelligence (AI) are providing the insurance industry with new opportunities to create tailored solutions and services based on newfound knowledge of consumers, and the execution of enhanced operations and business functions. However, insurance data is heterogeneous, and imbalanced class distribution with low frequency and high dimensions presents four major challenges to machine learning in real-world business. Traditional machine learning algorithms can typically only be applied to standard data sets, which are normally homogeneous and balanced. In this paper, we focus on an efficient cost-sensitive parallel learning framework (CPLF) to enhance insurance operations with a deep learning approach that does not require pre-processing. Our approach comprises a novel, unified, end-to-end cost-sensitive parallel neural network that learns real-world heterogeneous data. A specifically-designed cost-sensitive matrix then automatically generates a robust model for learning minority classifications, and the parameters of both the cost-sensitive matrix and the hybrid neural network are alternately but jointly optimized during training. We also study the CPLF-based architecture for a real-world insurance intelligence operation system, and demonstrate fraud detection experiments on this system. The results of comparative experiments on real-world insurance data sets reflecting actual business cases demonstrate the effectiveness of our design.

Original languageEnglish
Pages (from-to)9713-9723
Number of pages11
JournalIEEE Transactions on Industrial Electronics
Volume66
Issue number12
DOIs
Publication statusPublished - Dec 2019
Externally publishedYes

Keywords

  • deep learning
  • heterogeneous data
  • imbalanced data
  • insurance operation
  • neural network

Cite this