Optimizing Logistic Regression for Flawless Fraud Detection in Digital Payments

被引:0
作者
Kant, Vishnu [1 ]
机构
[1] Chitkara Univ, Inst Engn & Technol, Rajpura, Punjab, India
来源
2024 SECOND INTERNATIONAL CONFERENCE ON INTELLIGENT CYBER PHYSICAL SYSTEMS AND INTERNET OF THINGS, ICOICI 2024 | 2024年
关键词
Artificial Intelligence; Deep Learning; Fraud Detection; Logistic Regression; Machine Learning; E-commerce Security; Financial Transactions; Binary Classification; Model Validation; Predictive Analytics; Data Pre-processing; MODEL;
D O I
10.1109/ICOICI62503.2024.10696469
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The rise in online transactions and e-commerce in the digital era has resulted in more fraudulent activity, which presents major difficulties for financial institutions and internet stores. Often depending on manual inspection and rule-based systems, traditional fraud detection techniques fight against advanced and high-volume fraud. the logistic regression across the real-world transaction data. Examining strategies to improve predictive power, it contrasts the performance of the model against conventional approaches and other machine learning systems. It highlights the benefits of applying the logistic regression for fraud detection, so supporting sustainable development goals including industry innovation, lower inequality, and strong institutions by means of insights and methods to help businesses protect their customers and lower financial losses.
引用
收藏
页码:97 / 100
页数:4
相关论文
empty
未找到相关数据