Analysis of Credit Card Fraud Detection Performance Using Random Forest Classifier & Neural Networks Model
Journal Title: Engineering and Technology Journal - Year 2024, Vol 9, Issue 02
Abstract
This research discusses credit card fraud detection using machine learning algorithms, specifically Random Forest Classifier and Neural Networks. Research methods include the EDA (Exploratory Data Analysis) stage, data preprocessing, building Random Forest and Neural Networks models, as well as model evaluation. The data used comes from the Kaggle dataset that has been provided. Data analysis is carried out using Pandas to understand the structure and content of the data, while preprocessing involves checking for duplicates, displaying data information, and statistical descriptions. The research results show that the Random Forest model achieved an accuracy of 96% in detecting credit card fraud, while Neural Networks also provided good results. A comparison of the performance of the two algorithms shows that both are effective in detecting fraud. Suggestions for further development include comparing the performance of the model with other algorithms, exploring the factors that influence fraud detection, and developing a more complex and adaptive detection system. The positive implication of the results of this research is increased efficiency in credit card fraud detection, which can provide major benefits in protecting consumers and financial institutions from detrimental fraudulent activities. References used in the research are also included to support the validity and accuracy of the findings obtained
Authors and Affiliations
Steven Wijaya,Wilfredo Wesly, Kristina Ginting, Abdi Dharma,
Keywords
Related Articles
- EP ID EP731072
- DOI 10.47191/etj/v9i02.11
- Views 29
- Downloads 0
PROBLEM SOLVING AND REHABILITATION OF THE SPELEOLOGICAL OBJECT OF LARGER DIMENSIONS WHICH APPEARED DURING THE EXCAVATION OF THE "POČITELJ" TUNNEL
The "Počitelj" tunnel was built as part of the section of the highway Mostar North - the border with the Republic of Croatia on the corridor Vc, the section Počitelj - Bijača, the subsection Počitelj - Zvirovići with a l...
UTILIZATION OF MARLSTONE POWDER TO INCREASE THE COMPRESSIVE STRENGTH OF CONCRETE
Marl is limestone mixed with clay that is formed through the process of sedimentation. In this study, the authors used marl in the form of powder originating from the outskirts of the Komering Martapura river because mar...
INVESTIGATION OF MODEL TRANSFORMER INSULATION BEHAVIOR DURING PD ACTIVITY IN DI-BENZO-DI-SULFIDE SULPHUR CONTAMINATED TRANSFORMER OIL USING ONLINE TAN DELTA MEASUREMENT
Sulphur can be present in mineral insulating oil and can manifest in stable, highly reactive and corrosive form. The corrosive sulphur reacts with the copper conductor in transformer and forms semi conductive copper sulp...
A REVIEW ON APPLICATIONS OF METAHEURISTIC ALGORITHMS IN MULTILEVEL THRESHOLDING IMAGE SEGMENTATION
In the field of image analysis, segmentation is one of the most important pre-processing steps. One way to achieve segmentation is the use of threshold selection. In particular, multilevel image thresholding is a very im...
Analysis of Service Level of Trans Metro Pasundan Bandung Raya Corridor 2 Based on Importance Performance Analysis and Customer Satisfaction Index
Trans Metro Pasundan is an integrated highway bus system serving the Greater Bandung metropolitan area, West Java. This service is a program from the Ministry of Transportation of the Republic of Indonesia through the Di...