Onunkwo, Clara (2019) A classification-based approach for modelling disputed responses based on consumer complaint on financial products. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (887kB) | Preview |
Preview |
PDF (Configuration manual)
Download (381kB) | Preview |
Abstract
This study is carried out with the purpose of creating and selecting the model with the highest performance rate among other models that can be used in predicting the likelihood of consumers disputing complaints responses made by financial service providers regarding products and services. This study purpose was as a result of the problem faced by financial service providers where responses provided based on complaints raised are disputed by the consumers. The financial service providers view this act as a problem to their services and which calls for solutions. This act could be said to have implications on the quality of financial service and thus affecting consumers satisfaction. For this reason, the study applies three classification model such as Naive Bayes, Random Forest and Logistic Regression to help achieve its purpose and this will be determined based on the accuracy rate of each models. Based on the various analysis carried out on each model, Random Forest presented itself with the highest accuracy rate compared to Naive Bayes and Logistic Regression which presented a good accuracy rate but not as high as that of the Random forest. Based on this, Random Forest was selected as the best fit model to be used.
Keywords: consumer complaint, disputed response, naive bayes, random forest, logistic regression, financial service providers, prediction, financial products and
services.
Item Type: | Thesis (Masters) |
---|---|
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software H Social Sciences > HG Finance > Banking |
Divisions: | School of Computing > Master of Science in FinTech |
Depositing User: | Dan English |
Date Deposited: | 03 Jun 2020 10:10 |
Last Modified: | 03 Jun 2020 10:10 |
URI: | https://norma.ncirl.ie/id/eprint/4227 |
Actions (login required)
View Item |