Classify Credit Card User Segments through Transactional Behaviour Analysis Using Advanced Machine Learning Algorithms
Author : Dr. K Kalyani and G Sabitha
Abstract :
The rapid growth of digital payment systems has generated massive volumes of credit card transaction data, creating new opportunities for data-driven customer analysis. This study focuses on classifying credit card user segments by analyzing their transactional behaviour using advanced machine learning algorithms and sampling techniques. The objective is to identify distinct customer groups based on spending patterns, payment habits, and transaction frequency, enabling financial institutions to better understand customer behavior and improve targeted services. In this work, transactional datasets are preprocessed and balanced using appropriate sampling methods to address data imbalance issues. Various machine learning algorithms are applied to extract meaningful behavioural patterns and perform user segmentation effectively. The proposed approach enhances classification accuracy and improves the reliability of segmentation results. Experimental evaluation demonstrates that the integration of advanced ML models with sampling techniques significantly improves the performance of user classification compared to traditional methods. The results of this study can support banks and financial organizations in developing personalized marketing strategies, risk assessment models, and fraud detection systems. Ultimately, behavioural-based credit card segmentation can contribute to better customer relationship management and more efficient financial decision-making.
Keywords :
Credit Card Segmentation, Transactional Behaviour Analysis, Machine Learning, Sampling Methods, Customer Classification, Financial Data Analytics.
