NLP-Based Detection of Systematic Anomalies Among the Narratives of Consumer Complaints

32 Pages Posted: 28 Aug 2023 Last revised: 3 Dec 2023

See all articles by Peiheng Gao

Peiheng Gao

Western University, Canada

Ning Sun

Agri-Food Analytics Lab; Dalhousie University

Xuefeng Wang

Western University, Canada

Chen Yang

Icahn School of Medicine at Mount Sinai

Ricardas Zitikis

Western University

Date Written: August 21, 2023

Abstract

We develop an NLP-based procedure for detecting systematic nonmeritorious consumer complaints, simply called systematic anomalies, among complaint narratives. While classification algorithms are used to detect pronounced anomalies, in the case of smaller and frequent systematic anomalies, the algorithms may falter due to a variety of reasons, including technical ones as well as natural limitations of human analysts. Therefore, as the next step after classification, we convert the complaint narratives into quantitative data, which are then analyzed using an algorithm for detecting systematic anomalies. We illustrate the entire procedure using complaint narratives from the Consumer Complaint Database of the Consumer Financial Protection Bureau.

Keywords: consumer complaints, anomaly detection, classification, sentiment scores, Cobb-Douglas function, natural language processing

Suggested Citation

Gao, Peiheng and Sun, Ning and Wang, Xuefeng and Yang, Chen and Zitikis, Ricardas, NLP-Based Detection of Systematic Anomalies Among the Narratives of Consumer Complaints (August 21, 2023). Available at SSRN: https://ssrn.com/abstract=4547452 or http://dx.doi.org/10.2139/ssrn.4547452

Peiheng Gao

Western University, Canada ( email )

Ning Sun

Agri-Food Analytics Lab ( email )

6100 University Avenue
Halifax, Nova Scotial
Halifax
Canada

Dalhousie University ( email )

6100 University Avenue
Halifax, Nova Scotia
Canada

Xuefeng Wang

Western University, Canada ( email )

Chen Yang (Contact Author)

Icahn School of Medicine at Mount Sinai ( email )

United States

Ricardas Zitikis

Western University ( email )

1151 Richmond Street
Suite 2
London, Ontario N6A 5B8
Canada

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
30
Abstract Views
213
PlumX Metrics