TY - JOUR
T1 - An Artificial Intelligence Approach to Financial Fraud Detection under IoT Environment
T2 - A Survey and Implementation
AU - Choi, Dahee
AU - Lee, Kyungho
N1 - Publisher Copyright:
© 2018 Dahee Choi and Kyungho Lee.
PY - 2018
Y1 - 2018
N2 - Financial fraud under IoT environment refers to the unauthorized use of mobile transaction using mobile platform through identity theft or credit card stealing to obtain money fraudulently. Financial fraud under IoT environment is the fast-growing issue through the emergence of smartphone and online transition services. In the real world, a highly accurate process of financial fraud detection under IoT environment is needed since financial fraud causes financial loss. Therefore, we have surveyed financial fraud methods using machine learning and deep learning methodology, mainly from 2016 to 2018, and proposed a process for accurate fraud detection based on the advantages and limitations of each research. Moreover, our approach proposed the overall process of detecting financial fraud based on machine learning and compared with artificial neural networks approach to detect fraud and process large amounts of financial data. To detect financial fraud and process large amounts of financial data, our proposed process includes feature selection, sampling, and applying supervised and unsupervised algorithms. The final model was validated by the actual financial transaction data occurring in Korea, 2015.
AB - Financial fraud under IoT environment refers to the unauthorized use of mobile transaction using mobile platform through identity theft or credit card stealing to obtain money fraudulently. Financial fraud under IoT environment is the fast-growing issue through the emergence of smartphone and online transition services. In the real world, a highly accurate process of financial fraud detection under IoT environment is needed since financial fraud causes financial loss. Therefore, we have surveyed financial fraud methods using machine learning and deep learning methodology, mainly from 2016 to 2018, and proposed a process for accurate fraud detection based on the advantages and limitations of each research. Moreover, our approach proposed the overall process of detecting financial fraud based on machine learning and compared with artificial neural networks approach to detect fraud and process large amounts of financial data. To detect financial fraud and process large amounts of financial data, our proposed process includes feature selection, sampling, and applying supervised and unsupervised algorithms. The final model was validated by the actual financial transaction data occurring in Korea, 2015.
UR - http://www.scopus.com/inward/record.url?scp=85056528230&partnerID=8YFLogxK
U2 - 10.1155/2018/5483472
DO - 10.1155/2018/5483472
M3 - Review article
AN - SCOPUS:85056528230
SN - 1939-0114
VL - 2018
JO - Security and Communication Networks
JF - Security and Communication Networks
M1 - 5483472
ER -