International Journal of Advanced Networking and Applications

Rifat Al Mamun Rudro ¹, Md. Faruk Abdullah Al Sohan ²

Affiliations
1 Department of Computer Science and Engineering, American International University, BD
2 Department of Computer Science, American International University, BD

Abstract

Credit card fraud transactions have been one of the most difficult issues for banks and other financial institutions in recent years. In such events, billions of dollars are lost by financial institutions and the banking system. Concurrently, user information is not safe for that purpose. To address these issues, this paper proposes an efficient solution to automate the task using machine learning techniques such as SMOTE and ADASYN. This paper also intends to run machine learning supervised models. We discovered class imbalancing issues after examining the experiment outcomes on European cardholder datasets. Oversampling and under sampling strategies are utilized to solve fraud situations to avoid them. Predictive models such as the LR, K-nearest neighbors, decision tree, random forest XGBoost, and support vector machines are utilized to achieve the model accuracy required to find the most fit-able models for credit card fraud. The performance of SMOTE machine learning approaches increased with a 0.96 model accuracy in random forest and XGBoost.

Keywords

SMOTE, ADASYN, XGBoost, Machine Learning, SVM, Precision, Recall

Full Text

   

Md. Faruk Abdullah AL Sohan ¹, Nusrat Jahan Trisna ¹, Rahul Das Joy ¹

Affiliations
1 Department of Computer Science, American International University-Bangladesh, BD

Abstract

Fake news threatens public debate and decision-making in a digital age. This comprehensive paper, "Unmasking Deception," methodically covers false news detecting tactics and technology. We summarize a wide range of study results, methods, and technological advances to give a thorough overview of disinformation detection and mitigation. Our research covers linguistic, content-based, machine learning, and deep learning false news identification. We examine emerging misleading strategies and propose novel remedies using natural language processing, network analysis, and other innovative methods. In addition, we evaluate current detection systems in real-world circumstances and address the ethical implications of their use. The findings of the research help scholars, policymakers, and technology developers understand false news and advance the area. The primary objective is to enhance the safeguarding of the information environment against misinformation by a critical evaluation of existing methodologies.

Keywords

false, detection, digital, debate, decision-making, ecosystem.

Full Text