Anomaly Detection in Credit Card Transactions using Machine Learning
Journal Title: International Journal of Innovative Research in Computer Science and Technology - Year 2020, Vol 8, Issue 3
Abstract
Anomaly Detection is a method of identifying the suspicious occurrence of events and data items that could create problems for the concerned authorities. Data anomalies are usually associated with issues such as security issues, server crashes, bank fraud, building structural flaws, clinical defects, and many more. Credit card fraud has now become a massive and significant problem in today's climate of digital money. These transactions carried out with such elegance as to be similar to the legitimate one. So, this research paper aims to develop an automatic, highly efficient classifier for fraud detection that can identify fraudulent transactions on credit cards. Researchers have suggested many fraud detection methods and models, the use of different algorithms to identify fraud patterns. In this study, we review the Isolation forest, which is a machine learning technique to train the system with the help of H2O.ai. The Isolation Forest was not so much used and explored in the area of anomaly detection. The overall performance of the version evaluated primarily based on widely-accepted metrics: precision and recall. The test data used in our research come from Kaggle.
Authors and Affiliations
Meenu, Swati Gupta, Sanjay Patel, Surender Kumar, Goldi Chauhan
Keywords
Related Articles
- EP ID EP747800
- DOI 10.21276/ijircst.2020.8.3.5
- Views 39
- Downloads 0
Power Quality Improvement in Distributed Generation using DSTATCOM and Photovoltaic Power Controller
Conventional energy sources like coal, nuclear energy sources, water, and other fossil fuels are getting depleted day by day. The availability of these resources is limited and would be exhausted one day. Therefore peopl...
Critical Evaluation on WSNs Positioning Methods
WSN gained a lot of attention because they are small and economical devices with low power utilization, and finite computing resources are progressively being enfolded in various application situations, including environ...
Prediction of Health Care Data Using Efficient Machine Learning Algorithms
Every clinical decision relies on the doctor's expertise and comprehension.This standard procedure may, despite appearances, lead to errors, biases, and increased costs that compromise the patients' Quality of Service (Q...
COMPARATIVE PERFORMANCE STUDY OF HYBRID ROUTING PROTOCOL OVER REAL TIME DATA IN MANET
MANET is a collection of wireless nodes that can dynamically form a network to exchange information without using any pre-existing fixed network infrastructure with or without centralized network controller. MANETs are b...
The Importance of Website Usability in Digital Marketing- A Review
The effectiveness of any digital marketing strategy is strongly dependent on the user experience of the website being promoted. A website that is difficult to browse, confusing or slow to load the content can result in a...