NORMA eResearch @NCI Library

Enhancing Customer Complaint Classification in Banking: A Deep Learning and Natural Language Processing Approach

Baskaran, Pratheep Kumar (2023) Enhancing Customer Complaint Classification in Banking: A Deep Learning and Natural Language Processing Approach. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (3MB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (2MB) | Preview

Abstract

This research pursued a new approach to classify customer feedback in banks using a blend of language processing methods and deep learning technologies. Approach involved a thorough preparation of the data, including converting text to lowercase, reducing words to their base forms, segmenting sentences into words, and omitting common yet non-critical words. The data was also customized to correspond with specific banking products using unique methods. In this study, a key part was experimenting with different high-level models A significant part of the study involved exploring various advanced models. I worked with several types, including CNN, LSTM, and BI-LSTM. These models were applied to two kinds of data: one set that underwent extensive cleaning and another that was processed similarly, but without aligning it with keywords. The findings revealed that the BI-LSTM model excelled, achieving 85% accuracy with keyword matching and 80% without it. Following these insights, a user-friendly interface was crafted for streamlined complaint classification, significantly improving how banks handle and respond to customer complaints. This enhancement in operational efficiency underscores the BI-LSTM model’s capability in the detailed task of complaint classification and the broader potential of deep learning in refining essential banking processes.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Anant, Aaloka
UNSPECIFIED
Subjects: H Social Sciences > HG Finance
Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
H Social Sciences > HG Finance > Banking
P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing
H Social Sciences > HF Commerce > Customer Service
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Ciara O'Brien
Date Deposited: 07 May 2025 10:41
Last Modified: 07 May 2025 10:41
URI: https://norma.ncirl.ie/id/eprint/7496

Actions (login required)

View Item View Item