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

Paper: arXiv 2308.11138

Authors: Peiheng Gao, Ning Sun, Xuefeng Wang, Chen Yang, Ričardas Zitikis

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.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 6.5/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper introduces a practical NLP and quantitative pipeline to identify subtle, systematic nonmeritorious consumer complaints that standard classifiers miss. While the underlying mathematical modeling is straightforward, the empirical application to public CFPB data provides solid practical utility and novel workflow design.

Research Flowchart

  flowchart TD
    A[Research Goal: Detect Systematic Anomalies in Consumer Complaints] --> B[(CFPB Consumer Complaint Database)]
    B --> C[Step 1: Classification Algorithms]
    C --> D[Step 2: Vectorize/Convert Text Narratives to Quantitative Data]
    D --> E[Step 3: Systematic Anomaly Detection Algorithm]
    E --> F[Outcome: Identification of Small, Frequent Nonmeritorious Complaints]