18 Sep Fraud Detection System Using Machine Learning: Fraud Detection through Machine Learning enables the system users to run an automated transaction processing on the dataset. The invo
write a 1.5 page research hypothesis based on the proposed project attached. Include several references.
this is the data i will be using for machine learning.
Name of Student
Fraud Detection System Using Machine Learning
Fraud Detection through Machine Learning enables the system users to run an automated transaction processing on the dataset. The involved Machine Learning model detects all potential fraudulent activities and flags. The fraud detection system using Machine learning remains the future for fraud detection in every financial institution since the ancient rules-based fraud detection systems have failed in their detection role since they cannot align with current technological advancements.
The Project Idea
The primary idea of this project is to facilitate self-learning to enable the system to adapt to new, unknown fraud patterns for detection. Unlike rules-based systems, this idea is based on machine learning, noting the fraudulent transactions that portray strange trends that are different from genuine ones. Machine learning algorithms detect the trends and can differentiate those between scammers and authentic customers (Akinbohun & Atanlogun, 2018). In the banking industry, this idea has successfully helped banks eliminate fraudulent transactions by fraudsters.
Furthermore, the implementation will immediately replace inconsistent and ineffective traditional fraud detection techniques. Over the past decades, banks, and other financial institutions have used rules-based systems associated with manual evaluation to detect fraud (Zhou et al., 2018). However, this project aligns with the current technology that has led fraudsters to increase in sophistication, such that the traditional systems cannot help anymore. The technology can assist machines in predicting and responding to suspicious activities in the system by fraudsters.
Work To Be Performed
This project's primary task is collecting and clustering the previously recorded data for fraud prevention and risk management programs. The gathered data will include information regarding legitimate and fraudulent transactions (Mallidi & Zagabathuni, 2021). After collection, the data will have a 'legitimate or fraudulent transactions or clients' label.
After collection, the data will be used to "teach" the machine learning software to detect whether a specific client or transaction is fraudulent or legitimate. A successful fraud detection system will need to gather more data on fraud trends. This maximum data collection will have many examples that algorithms can learn for accurate detection (Mallidi & Zagabathuni, 2021). After training the machine learning algorithm, the software becomes specific to the transactions and is said to be ready for use in the fraud management model. Therefore, the work will primarily train the algorithm by subjecting it to as huge data as possible to learn the patterns and update it from time to time since it is not infallible.
The project manager, the bank director (project sponsor), bank employees, and the software developers are involved.
Literature Review Behind the Motivation for Doing Project
According to Yee et al. (2018), the dominance of online-related transactional activities has raised fraudulent incidences worldwide. These activities have contributed to considerable losses to individuals and the banking sector. Despite the presence of multiple cybercrime practices within the banking sector, credit card fraudulent activities dominate, making online customers vulnerable to losing their money. Therefore, Yee et al. (2018) demonstrate that preventing fraud activities via a machine learning and data mining is a crucial strategy for eliminating illegal monetary acts. Initially, data mining approaches played a critical role in studying the trends and characteristics of legitimate and fraudulent transactions based on anomalies and normalized data.
Akinbohun, F., & Atanlogun, S. K. (2018). Credit Card Fraud Detection System in Commercial Sites. European Journal of Engineering and Technology Research, 3(11), 1-5.
Mallidi, M. K. R., & Zagabathuni, Y. (2021). Analysis of Credit Card Fraud Detection using Machine Learning models on balanced and imbalanced datasets. International Journal of Emerging Trends in Engineering Research, 9(7).
Yee, O. S., Sagadevan, S., & Malim, N. H. A. H. (2018). Credit card fraud detection using machine learning as data mining technique. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 10(1-4), 23-27.
Zhou, H., Chai, H. F., & Qiu, M. L. (2018). Fraud detection within bankcard enrollment on mobile device based payment using machine learning. Frontiers of Information Technology & Electronic Engineering, 19(12), 1537-1545.