Employing Advanced TCN Model to Predict the Success of Bank Telemarketing in Long-term Deposit Subscription

Lalu, Melin Mary (2024) Employing Advanced TCN Model to Predict the Success of Bank Telemarketing in Long-term Deposit Subscription. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (899kB) | Preview
Preview	PDF (Configuration Manual) Download (416kB) | Preview

Abstract

This research focuses on predicting the success of bank telemarketing campaigns in securing subscriptions to long-term deposits, leveraging the power of Temporal Convolutional Networks (TCNs). TCNs are well-suited for sequential data analysis, allowing the capture of temporal patterns in customer interactions, a critical factor in telemarketing. The study addresses challenges such as data imbalance, high dimensionality, and nonlinear relationships that hinder the predictive power of traditional statistical and machine learning methods. The dataset, sourced from the UCI Machine Learning Repository, underwent comprehensive preprocessing, including handling missing values, encoding categorical variables, and addressing class imbalance using SMOTE. A comprehensive TCN model was designed and implemented, with performance evaluated against traditional models like Support Vector Machines (SVM), Decision Trees, Naïve Bayes, and advanced techniques such as Artificial Neural Networks (ANN) and K-nearest neighbors (KNN). Evaluation metrics including accuracy, F1-score, and AUC-ROC highlighted TCN's superior capability, achieving balanced performance in identifying potential subscribers despite the imbalanced nature of the data. The findings underline TCN's effectiveness in telemarketing prediction tasks, offering financial institutions a robust tool for optimizing campaign strategies. The research establishes TCN as a promising approach to improving customer acquisition and retention in the financial sector.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Yaqoob, Abid 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 Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HF Commerce > Marketing
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	03 Sep 2025 11:10
Last Modified:	03 Sep 2025 11:10
URI:	https://norma.ncirl.ie/id/eprint/8733

Actions (login required)

View Item