Implementing Ensemble Method with stacking approach for Machine Learning and Deep Learning Algorithms for Credit Card Fraud Detection

Marlabeedu, Charan Teja (2024) Implementing Ensemble Method with stacking approach for Machine Learning and Deep Learning Algorithms for Credit Card Fraud Detection. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (5MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

In the present world a use of online financial transactions has led to increase in risk of credit card fraud, which is major issue for consumers along with financial institutions alike. Improving approaches for detecting a fraud via combination/integration of deep learning & machine learning is major topic of our research. This study aims to evaluate an efficacy of ”stacked” approach to fraud detection by a combining several prediction models. Research is divided in 3 distinct case studies. As first one demonstrates, there is lot of promise into combining a different machine learning models, yet it can be rather difficult. Second research demonstrates that deep learning methods, namely CNNs & RNNs, are superior at detecting most typical fraud patterns. A hybrid model combining a stacked ML & stacked DL is tested into third trial. Its crucial to select & fine-tune primary model which incorporates all of models, as shown by extensive testing into thesis, even if combining multiple models might improve performance. Study represents the significant advancement into field of fraud detection, paving way for more robust & adaptable systems to ensure security of online financial transactions. The proposed models as per a research implementing the stacking approach for the machine learning and deep learning has shown the promising results with accuracy 92.472%, Precision 0.912, Recall 0.934 and f1score 0.923 than the individual models performance.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Milosavljevic, Vladimir UNSPECIFIED
Uncontrolled Keywords:	machine learning and deep learning model; predictive analytics; fraud detections; stacking approach; meta models
Subjects:	H Social Sciences > HV Social pathology. Social and public welfare > Criminology > Crimes and Offences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HF Commerce > Electronic Commerce 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:	18 May 2025 13:16
Last Modified:	18 May 2025 13:16
URI:	https://norma.ncirl.ie/id/eprint/7567

Actions (login required)

View Item