Detection of shell companies in financial institutions using dynamic social network

Salazar, José de Jesús Rocha; Vargas, María Jesús Segovia; Miñano, María del Mar Camacho

doi:10.1016/j.eswa.2022.117981

Cited by 8 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An example of this can be seen in Ref. [17], where the authors show how the unsupervised machine learning algorithms such as the K-means, the neural gas and the principal component analysis significantly decrease false positive rates in the detection of money laundering and shell company activity.…”

Section: The Age Of Emerging Technologiesmentioning

confidence: 99%

Money Laundering in the Age of Cybercrime and Emerging Technologies

Rocha-Salazar,

Segovia-Vargas

2024

Corruption, Bribery, and Money Laundering - Global Issues

Self Cite

View full text Add to dashboard Cite

Historically, money laundering has been the financial crime of most significant interest in the international sphere due to the abrupt amounts of money it involves, the damage it causes to the institution’s reputation, and the government spending to combat it. Numerous international organizations, such as the Financial Action Task Force (FATF) and the United Nations (UN), stipulate standards and norms to regulate its prevention and detection. With the emergence of the 4th industrial revolution, technologies such as artificial intelligence, the Internet of Things (IoT), intelligent apps, cloud computing, and cybersecurity play roles in opposite directions in committing and combating money laundering. While artificial intelligence provides innovative models and algorithms capable of predicting money laundering activity, the Internet of Things and intelligent apps seem to create new means for cyber money laundering where cybersecurity comes as a mitigating measure. Bearing this in mind, the current chapter presents an overview of the impact of emerging technologies and cybercrime in executing and fighting against money laundering.

show abstract

Section: The Age Of Emerging Technologiesmentioning

confidence: 99%

Money Laundering in the Age of Cybercrime and Emerging Technologies

Rocha-Salazar,

Segovia-Vargas

2024

Corruption, Bribery, and Money Laundering - Global Issues

Self Cite

View full text Add to dashboard Cite

show abstract

“…By analyzing unstructured data, such as text or images, this integration can aid in identifying potential risks or fraudulent activities (Liu et al, 2023). Opportunities for integrating machine learning with other technologies, such as blockchain and natural language processing, could also improve the transparency and security of financial transactions, making it more difficult for fraudsters to exploit vulnerabilities in the system (Salazar et al, 2022). Another important direction for future research is the development of explainable and interpretable machine learning models (Nadella, G. S., & Vadakkethil Somanathan Pillai, S. E. 2024).…”

Section: Future Directions and Opportunitiesmentioning

confidence: 99%

Analyzing the Impact of Machine Learning Algorithms on Risk Management and Fraud Detection in Financial Institution

Kumar,

Singh

2024

Int. J. Res. Publ. Rev

View full text Add to dashboard Cite

This study examines the impact of machine learning algorithms on risk management and fraud detection in financial institutions. Machine learning has the potential to be integrated into various decision-making systems. In recent years, the ability of machine learning algorithms to analyze large datasets and provide precise predictions has attracted significant attention across multiple sectors. Accurate risk assessment and fraud prevention are crucial for financial institutions to avoid potential financial losses and damage to their reputation. Machine learning algorithms have enabled financial institutions to adopt more efficient and effective strategies to mitigate these risks. Financial institutions increasingly utilize machine learning algorithms to improve risk management and fraud detection. These algorithms employ advanced statistical techniques to analyze massive datasets and identify patterns and anomalies that may indicate potential risks or fraudulent activities. The most widely used machine learning algorithms in risk management and fraud detection are supervised learning algorithms like logistic regression and decision trees and unsupervised learning algorithms like clustering and anomaly detection. These algorithms can process and analyze vast amounts of data in real time, allowing financial institutions to detect and respond more effectively to potential risks and fraudulent activities.

show abstract