Tools
Tools
Sangotra, Ashreet (2022) Exploring differences in Consumer Complaint Behaviour in Financial Products and modelling disputed responses using classification techniques. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (5MB) | Preview |
Preview |
PDF (Configuration manual)
Download (366kB) | Preview |
Abstract
Consumers disputing the responses provided by companies to their complaints has been a growing concern, and a pain point for the respective companies. This study aims to build a machine learning model that can predict the likelihood of a complaint response to be disputed. This would help the companies identify those complaints, and proactively take measures to reduce the likelihood of further disputes. The study follows the CRISP-DM approach to this problem. Basic Machine learning classifiers such as Logistic Regression, Support Vector Machine and Random Forest are applied and assessed across various metrics. To improve baseline model performance, sampling techniques as well as NLP techniques have been further implemented. After conducting a thorough analysis across different models and metrics, Random Forest Classifier when applied to randomly under sampled data performs the best, and thus is our best fit model.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Consumer complaints; Random Forest Classifier; Logistic Regression; Support Vectors; Natural Language Processing; financial products; consumer behaviour |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HF Commerce > Marketing > Consumer Behaviour H Social Sciences > HG Finance > Financial Services |
| Divisions: | School of Computing > Master of Science in FinTech |
| Depositing User: | Clara Chan |
| Date Deposited: | 07 Nov 2022 14:51 |
| Last Modified: | 07 Nov 2022 14:51 |
| URI: | https://norma.ncirl.ie/id/eprint/5849 |
Actions (login required)
 |
View Item |