Javascript must be enabled to continue!
Legal system-oriented telecom fraud detection, identification and prevention
View through CrossRef
INTRODUCTION: With the development of technology, telecom fraud is appearing more and more frequently and causing more and more harm.OBJECTIVES: This paper focused on the detection, identification, and prevention of telecom fraud.METHODS: Firstly, the telecom fraud crime was analyzed, the existing legal system was explained, and some suggestions on the protection of telecom fraud were proposed at the legal level. Then, the characteristics of telecom fraud users were analyzed to point out the differences between fraud users and normal users in terms of call, message, and traffic behavior. Finally, the Boosting algorithm was used to detect and identify telecom fraud.RESULTS: The experiments found that the boosting algorithm had advantages in the detection and recognition of telecom fraud compared with the algorithms such as support vector machine and random forest algorithms. Among several boosting algorithms, the CatBoost algorithm performed the best, with an accuracy of 0.9465 and an F1 value of 0.9047.CONCLUSION: The results demonstrate the reliability of the CatBoost algorithm in detecting and recognizing telecom fraud, and it can be applied in practice.
European Alliance for Innovation n.o.
Title: Legal system-oriented telecom fraud detection, identification and prevention
Description:
INTRODUCTION: With the development of technology, telecom fraud is appearing more and more frequently and causing more and more harm.
OBJECTIVES: This paper focused on the detection, identification, and prevention of telecom fraud.
METHODS: Firstly, the telecom fraud crime was analyzed, the existing legal system was explained, and some suggestions on the protection of telecom fraud were proposed at the legal level.
Then, the characteristics of telecom fraud users were analyzed to point out the differences between fraud users and normal users in terms of call, message, and traffic behavior.
Finally, the Boosting algorithm was used to detect and identify telecom fraud.
RESULTS: The experiments found that the boosting algorithm had advantages in the detection and recognition of telecom fraud compared with the algorithms such as support vector machine and random forest algorithms.
Among several boosting algorithms, the CatBoost algorithm performed the best, with an accuracy of 0.
9465 and an F1 value of 0.
9047.
CONCLUSION: The results demonstrate the reliability of the CatBoost algorithm in detecting and recognizing telecom fraud, and it can be applied in practice.
Related Results
ANALISIS PENGARUH FAKTOR-FAKTOR PENYEBAB FRAUD DI SEKTOR PEMERINTAHAN KOTA BANJARBARU
ANALISIS PENGARUH FAKTOR-FAKTOR PENYEBAB FRAUD DI SEKTOR PEMERINTAHAN KOTA BANJARBARU
Abstract: Government agencies as budget users, implementers of popular programs and activities, are indicated to be real perpetrators of fraud. Some conditions in the work environm...
Design of an integrated e-Telecom system for improving telecom systems on ships
Design of an integrated e-Telecom system for improving telecom systems on ships
Abstract
The advancement of communication technologies including satellites has been conducive to the ever-evolving ship management. The increasing needs for the accident p...
Advanced frameworks for fraud detection leveraging quantum machine learning and data science in fintech ecosystems
Advanced frameworks for fraud detection leveraging quantum machine learning and data science in fintech ecosystems
The rapid expansion of the fintech sector has brought with it an increasing demand for robust and sophisticated fraud detection systems capable of managing large volumes of financi...
Evaluation of Fraud Prevention Policies in the National Health Insurance System in Indonesia: Narrative Literature Review
Evaluation of Fraud Prevention Policies in the National Health Insurance System in Indonesia: Narrative Literature Review
Introduction: Fraud in the National Health Insurance System (JKN) in Indonesia is a serious issue that harms health services and financing. Fraud practices such as phantom billing ...
A Graph Neural Network Model for Financial Fraud Prevention
A Graph Neural Network Model for Financial Fraud Prevention
Financial fraud prevention is a critical challenge for banks, payment processors, and online financial services. Traditional fraud detection models, including rule-based systems an...
Integrating machine learning and blockchain: Conceptual frameworks for real-time fraud detection and prevention
Integrating machine learning and blockchain: Conceptual frameworks for real-time fraud detection and prevention
Integrating machine learning (ML) and blockchain technologies presents a groundbreaking approach to real-time fraud detection and prevention, addressing the growing complexity and ...
Autonomy on Trial
Autonomy on Trial
Photo by CHUTTERSNAP on Unsplash
Abstract
This paper critically examines how US bioethics and health law conceptualize patient autonomy, contrasting the rights-based, individualist...
A predictive analytics model for banking fraud detection: Solving real-time challenges in customer safety and financial security
A predictive analytics model for banking fraud detection: Solving real-time challenges in customer safety and financial security
The rise in banking fraud has highlighted the critical need for robust and efficient fraud detection systems that ensure customer safety and financial security. Existing methods of...

