NLP-based detection of systematic anomalies among the narratives of consumer complaints

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gao, Peiheng, Sun, Ning, Wang, Xuefeng, Yang, Chen, Zitikis, Ričardas
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929290225909760
author Gao, Peiheng
Sun, Ning
Wang, Xuefeng
Yang, Chen
Zitikis, Ričardas
author_facet Gao, Peiheng
Sun, Ning
Wang, Xuefeng
Yang, Chen
Zitikis, Ričardas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_11138
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle NLP-based detection of systematic anomalies among the narratives of consumer complaints
Gao, Peiheng
Sun, Ning
Wang, Xuefeng
Yang, Chen
Zitikis, Ričardas
Methodology
Computation and Language
Risk Management
Machine Learning
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.
title NLP-based detection of systematic anomalies among the narratives of consumer complaints
topic Methodology
Computation and Language
Risk Management
Machine Learning
url https://arxiv.org/abs/2308.11138