Use of data warehousing to analyze customer complaint data of Consumer Financial Protection Bureau of United States of America

Abstract

The Consumer Financial Protection Bureau was established in USA for enabling the USA consumers to report customer support and complaint related information regarding their financial issues with the US government. The complaint data is freely available for analysis and tracking of how efficiently and effectively the financial institutes handle the complaints lodged against them. Each complaint consists of attributes that can uniquely describe and identify it. These features have been exploited for data mining, analysis and predictions. The data warehouse creation and data analysis was done using Microsoft SQL Server Technologies. The data mining techniques such as Microsoft Decision Tree, Microsoft Naïve Bayes, Microsoft Time Series and Microsoft Neural Network models were used in this study. Based on the results, it was observed that there is a correlation between the growth of complaints in certain financial domains with regards to changes in the economic, political and regulatory forces. Probability predictions also show, how each product can get a particular issue-related complaint, how a particular issue can get a timely response, how a particular issue can cause a consumer dispute and what type of issues are mostly lodged via a particular submission method, etc. This information can be used in prescriptive analysis to enhance financial consumer services and also improve the response quality of automated consumer support systems.