• The Journal of Society for e-Business Studies
• /
• v.27 no.2
• /
• pp.65-77
• /
• 2022

Due to the recent development in electronic financial services, transactions of electronic prepayment are rapidly growing, leading to growing fraud attempts. This paper proposes a methodology that can effectively detect fraud transactions in electronic prepayment by machine learning algorithms, including support vector machines, decision trees, and artificial neural networks. Actual transaction data of electronic prepayment services were collected and preprocessed to extract the most relevant variables from raw data. Two different approaches were explored in the paper. One is a transaction-based approach, and the other is a user ID-based approach. For the transaction-based approach, the first model is primarily based on raw data features, while the second model uses extra features in addition to the first model. The user ID-based approach also used feature engineering to extract and transform the most relevant features. Overall, the user ID-based approach showed a better performance than the transaction-based approach, where the artificial neural networks showed the best performance. The proposed method could be used to reduce the damage caused by financial accidents by detecting and blocking fraud attempts.

• The Journal of Society for e-Business Studies
• /
• v.11 no.4
• /
• pp.87-106
• /
• 2006

Today as the scale of e-commerce constantly expands, the number and the amount of the consumer frauds are also increasing very rapidly, without sufficient levels of systematic support to prevent them. Internet Escrow service is one of the promising payment mechanisms, which guarantees secure electronic trades and payments. Especially, if the real-time product delivery information is available via RFID-based track-and-trace environment, the security and efficiency of the Internet Escrow services would be improved a lot. In this research, proposed a novel approach to integrate EPCglobal Network, which is a de-facto standard for RFID-based information network model, with Internet Escrow services. The proposed service model was implemented in the form of "Integrated Financial Platform", which supports the contracts among trading partners and the payment via Escrow services by being fully integrated with bank systems. Using the implemented EPCglobal Network-based Escrow service system, we would be able not only to shorten the money-flow cycle and to develop new kinds of loan services, but also to overcome the problems of existing Escrow services including the lack of product-related information and the delay of purchasing decisions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.9
• /
• pp.6282-6289
• /
• 2015

Today, there is an increasing number of cases in which certificate information is leak, and accordingly, electronic finance frauds are prevailing. As certificate and private key a file-based medium, are easily accessible and duplicated, they are vulnerable to information leaking crimes by cyber-attack using malignant codes such as pharming, phishing and smishing. Therefore, the use of security token and storage toke' has been encouraged as they are much safer medium, but the actual users are only minimal due to the reasons such as the risk of loss, high costs and so on. This thesis, in an effort to solve above-mentioned problems and to complement the shortcomings, proposes a system in which digital signature for Internet banking can be made with a simply bio-authentication process. In conclusion, it was found that the newly proposed system showed a better capability in handling financial transitions in terms of safety and convenience.

• Korean Journal of Social Welfare Studies
• /
• v.47 no.4
• /
• pp.151-181
• /
• 2016

The objective of the study is to identify the sub-path of entry into homelessness of young men and enhance understanding them. In specific, homeless risk factors were extracted through their experiences, and based on which the entry paths into homelessness were drawn. The homeless young adults were divided into two groups of those who became homeless in their adolescence and those who entered into homelessness after 19 and their differences were analyzed. As a results, the most prominent differences between the two sub-groups included individual and social factors; most of those who entered homelessness after 19 had physical or psychological problems, while the other group showed delinquency factors in adolescence and adulthood. As for social factors, the former group experienced more financial damage in the process of achieving independence before being homeless, while the latter group had relatively more experience of physical and psychological damage such as bullying, harassment and violence before being homeless and financial frauds. As for investigating the causality relationship of key homeless risk factors by adding a variable of time, and based on which, a constant pattern of entry paths toward homelessness was drawn among each sub-group of homeless young adults. For policy on homelessness, it is required to develop according to the characteristics of homeless young adults. Especially, a specific approach is necessary for the different homeless pathways by sub-group. Furthermore, the study indicated that management and preemptive responses for various homeless risk factors that homeless young adults experienced throughout their lifetime could be important prevention policy against homelessness.