Latent Dirichlet allocation (LDA) for topic modeling of the CFPB consumer complaints

作者：

Highlights：

• The Consumer Financial Protection Bureau takes consumer complaint narratives.

• A decision support system (DSS) for CFPB consumer complaint analysis is proposed.

• The mechanism is based on topic modeling to automatically reveal consumer issues.

• The extracted topics reveal interesting insights into the financial community.

• Success of federal consumer protection regulations are examined via the proposed DSS.

摘要

•The Consumer Financial Protection Bureau takes consumer complaint narratives.•A decision support system (DSS) for CFPB consumer complaint analysis is proposed.•The mechanism is based on topic modeling to automatically reveal consumer issues.•The extracted topics reveal interesting insights into the financial community.•Success of federal consumer protection regulations are examined via the proposed DSS.

论文关键词：Analytics,Latent Dirichlet allocation,Topic modeling,CFPB,Decision support system,Consumer complaint narratives

论文评审过程：Received 22 July 2018, Revised 20 February 2019, Accepted 1 March 2019, Available online 7 March 2019, Version of Record 16 March 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.03.001