Analysis of customer complaint data of consumer financial protection bureau using different text mining techniques

No Thumbnail Available
Authors
Shivaprasad, Vageesh
Issue Date
2020
Degree
MSc in Data Analytics
Publisher
Dublin Business School
Rights
Items in eSource are protected by copyright. Previously published items are made available in accordance with the copyright policy of the publisher/copyright holder.
Abstract
The Consumer Financial Protection Bureau is a federal agency responsible for protecting rights of retail consumers. The agency was established in USA for enabling the USA consumers to report complaint and support related information regarding their respective financial concerns with the federal government. The Consumer Complaint Database is a collection of complaints received by Consumer Finance Protection Bureau on a range of consumer financial products and services offered by banks and other financial institutions across the United States of America. There is no licensing associated with the data and is intended for public access and use. Each complaint consists of attributes that can uniquely describe and identify it. These features have been utilized for data analysis and predictions. In this paper we are using text classification techniques like Naïve Bayes, Decision Tree, Generalized Linear Model, Fast Large Margin, Deep learning and Support Vector Classifier in Rapid miner tool to classify the consumer complaints into respective product or service offered by the financial institutions. This information can be used in prescriptive analysis to enhance financial consumer services and improve the response quality of automated consumer support systems.