• Information Systems Review
• /
• v.22 no.1
• /
• pp.59-72
• /
• 2020

Artificial Intelligence is establishing itself as a familiar tool from an intractable concept. In this trend, financial sector is also looking to improve the problem of existing system which includes Fraud Detection System (FDS). It is being difficult to detect sophisticated cyber financial fraud using original rule-based FDS. This is because diversification of payment environment and increasing number of electronic financial transactions has been emerged. In order to overcome present FDS, this paper suggests 3 types of artificial intelligence models, Generative Adversarial Network (GAN), Deep Neural Network (DNN), and Convolutional Neural Network (CNN). GAN proves how data imbalance problem can be developed while DNN and CNN show how abnormal financial trading patterns can be precisely detected. In conclusion, among the experiments on this paper, WGAN has the highest improvement effects on data imbalance problem. DNN model reflects more effects on fraud classification comparatively.

• 한국경영정보학회:학술대회논문집
• /
• 2007.06a
• /
• pp.597-602
• /
• 2007

데이터 마이닝 분야에서 앙상블 모형의 유용성은 널리 인정되고 있다. 앙상블을 구성하는 단위모형들 사이의 다양성이 보장되는 경우, 최종 모형의 정확성 및 안정성이 향상되기 때문이다. 하지만, 얼마나 많은 단위 모형들이 어떤 방식으로 결합되어야 하는가에 대해서는 아직도 더 많은 연구가 필요하다. 본 연구에서는 신용카드 부정사용 유형 중 하나인 현금불법융통 문제에 대해 앙상블 모형의 유용성을 검증하고자 한다. 부정행위 적발 모형은 전형적인 분류 문제의 한 유형이나, 클래스간 불균형이 매우 심하다는 특징이 있다. 따라서, 현금불법융통 문제에 적합한 다양성(Diversity) 척도를 개발하여 최소한의 단위모형들로 앙상블 모형을 구성하는 방안을 제시하였다. 축소된 앙상블 모형이 많은 수의 모형을 결합한 앙상블 모형과 거의 같은 정확성 및 안정성을 보임을 국내 신용카드사의 실제 자료를 사용하여 입증하였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.5
• /
• pp.113-130
• /
• 2011

Due to the development of information and communication technology, the global influence on politics, economics, society, and culture has grown. A major example of this impact on the economic sector is the growth of e-commerce, which increases both the speed and efficiency of businesses. In light of these new developments, businesses need to shift away from the misconception that information overwhelms to embrace the enhanced competitiveness that e-commerce provides. However, concern about fraudulent transactions through e-commerce is pertinent because of the loss in both critical revenue and consumer confidence in open markets. Current solutions for fraudulent transactions include real-time monitoring and processing, payment pending, and confirmation through SMS, E-mail, and other wired means. Our research focuses on the management of Fraud Detection Systems (FDS) to safeguard online electronic payment systems. With effective implementation of our research we hope to foster an honorable online trading culture and protect consumers. Future comparative research in domestic and abroad markets would provide further insight into preventing fraudulent transactions.

• Korean Management Science Review
• /
• v.21 no.2
• /
• pp.273-289
• /
• 2004

Although the Internet is useful for transferring information, Internet auction environments make fraud more attractive to offenders, because the chance of detection and punishment is decreased. One of these frauds is the phantom transaction, which is a colluding transaction by the buyer and seller to commit the illegal discounting of a credit card. They pretend to fulfill the transaction paid by credit card, without actually selling products, and the seller receives cash from the credit card corporations. Then the seller lends it out with quite a high interest rate to the buyer, whose credit rating is so poor that he cannot borrow money from anywhere else. The purpose of this study is to empirically investigate the factors necessary to detect phantom transactions in an online auction. Based upon studies that have explored the behaviors of buyers and sellers in online auctions, the following have been suggested as independent variables: bidding numbers, bid increments, sellers' credit, auction lengths, and starting bids. In this study. we developed Internet-based data collection software and collected data on transactions of notebook computers, each of which had a winning bid of over W one million. Data analysis with a logistic regression model revealed that starting bids, sellers' credit, and auction length were significant in detecting the phantom transactions.

• Information Systems Review
• /
• v.22 no.4
• /
• pp.135-161
• /
• 2020

With the growth of blockchain and cryptocurrency-related markets, cryptocurrency exchanges are growing as a new industry. However, as the legal and regulatory definitions of cryptocurrencies are still in progress, unlike existing industrial groups, they are not under the supervision of regulatory agencies. As a result, users (i.e., cryptocurrency investors) have suffered two types of damage that could occur from hacking and other accidents on the exchanges. One type of the damage is the loss of assets caused by the extortion of personal information or account and the other is the damage from users who might be involved in external frauds. Both are analyzed in comparison with existing operators whose functions are like the exchanges. The results of this study show that membership (KYC: Know Your Client), log-in, and additional authentication in transactions are on the similar level to those of the operators while the fraud detection system (FDS) and anti-money laundering (AML) of fiat currencies and cryptocurrencies need rapid improvement.

• Journal of KIBIM
• /
• v.13 no.3
• /
• pp.12-20
• /
• 2023

Deep learning-based anomaly detection technology is used in various fields such as computer vision, speech recognition, and natural language processing. In particular, this technology is applied in various fields such as monitoring manufacturing equipment abnormalities, detecting financial fraud, detecting network hacking, and detecting anomalies in medical images. However, in the field of construction and architecture, research on deep learning-based data anomaly detection technology is difficult due to the lack of digitization of domain knowledge due to late digital conversion, lack of learning data, and difficulties in collecting and processing field data in real time. This study acquires necessary data through IoT (Internet of Things) from the viewpoint of monitoring for environmental management of architectural spaces, converts them into a database, learns deep learning, and then supports anomaly patterns using AI (Artificial Infelligence) deep learning-based anomaly detection. We propose an implementation process. The results of this study suggest an effective environmental anomaly pattern detection solution architecture for environmental management of architectural spaces, proving its feasibility. The proposed method enables quick response through real-time data processing and analysis collected from IoT. In order to confirm the effectiveness of the proposed method, performance analysis is performed through prototype implementation to derive the results.

• Journal of Digital Convergence
• /
• v.11 no.10
• /
• pp.593-608
• /
• 2013

According to increasing number of injury claims, the challenge is reducing investigation of cases of injuries by selecting them more delicately, while also increasing the redemption rates and the amount of restitution. In this regards, we developed the fraud detection model for injury claims of self-employed insured by using decision tree after collecting medical claim data from 2006 to 2011 of the National Health Insurance in Korea. As a result of this model, subject types were classified into 18 types. If applying these types to the actual survey compared with if not applying, the redumption collecting rate will be increasing by 12.8%. Also, the effectiveness of this model will be maximize when the number of claims handlers considering their survey volume and management plans are examined thoroughly.

• The Journal of Economics, Marketing and Management
• /
• v.3 no.1
• /
• pp.33-39
• /
• 2015

Managers are always trying to be the best internal controls in their organizations copper approximate because they know that be effective internal control over previous systems, to fulfill the mission of the organization and minimize unexpected events will be extremely difficult. On the other hand, the existence of internal controls to increase efficiency, reduce head loss, assets and achieving a reasonable assurance of the reliability of financial statements and compliance with laws and regulations will be. Internal control, not an event, but a series of operations and activities on the basis of output. Internal controls help to achieve the goal of minimizing the problems of implementing appropriate internal controls. Internal control is an integral component of corporate governance that will provide reasonable assurance of achieving the organization's objectives. preventing, detecting errors and fraud goes to work. Responsibility for the prevention and detection of fraud and error in the public sector is the responsibility of managers. Managers of internal control and consistently applying appropriate accounting systems, this responsibility will play (Lin et al., 2011). Since the public sector organizations differ from each other, thus establishing internal controls cant be the same for all organizations and agencies of the public sector. Establish specific controls on each system to factors such as size, type of operation and organizational goals that the system is designed, it depends. On the other hand, rapid advances in information technology, the need to update internal control guidelines in relation to Create a new computer system so as to ensure that the activities of managers and effective control Should be updated if necessary.

• 대한예방의학회:학술대회논문집
• /
• 2002.10a
• /
• pp.338-339
• /
• 2002

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.119-138
• /
• 2017

Recently, SNS has become an important channel for marketing as well as personal communication. However, cybercrime has also evolved with the development of information and communication technology, and illegal advertising is distributed to SNS in large quantity. As a result, personal information is lost and even monetary damages occur more frequently. In this study, we propose a method to analyze which sentences and documents, which have been sent to the SNS, are related to financial fraud. First of all, as a conceptual framework, we developed a matrix of conceptual characteristics of cybercriminality on SNS and emergency management. We also suggested emergency management process which consists of Pre-Cybercriminality (e.g. risk identification) and Post-Cybercriminality steps. Among those we focused on risk identification in this paper. The main process consists of data collection, preprocessing and analysis. First, we selected two words 'daechul(loan)' and 'sachae(private loan)' as seed words and collected data with this word from SNS such as twitter. The collected data are given to the two researchers to decide whether they are related to the cybercriminality, particularly financial fraud, or not. Then we selected some of them as keywords if the vocabularies are related to the nominals and symbols. With the selected keywords, we searched and collected data from web materials such as twitter, news, blog, and more than 820,000 articles collected. The collected articles were refined through preprocessing and made into learning data. The preprocessing process is divided into performing morphological analysis step, removing stop words step, and selecting valid part-of-speech step. In the morphological analysis step, a complex sentence is transformed into some morpheme units to enable mechanical analysis. In the removing stop words step, non-lexical elements such as numbers, punctuation marks, and double spaces are removed from the text. In the step of selecting valid part-of-speech, only two kinds of nouns and symbols are considered. Since nouns could refer to things, the intent of message is expressed better than the other part-of-speech. Moreover, the more illegal the text is, the more frequently symbols are used. The selected data is given 'legal' or 'illegal'. To make the selected data as learning data through the preprocessing process, it is necessary to classify whether each data is legitimate or not. The processed data is then converted into Corpus type and Document-Term Matrix. Finally, the two types of 'legal' and 'illegal' files were mixed and randomly divided into learning data set and test data set. In this study, we set the learning data as 70% and the test data as 30%. SVM was used as the discrimination algorithm. Since SVM requires gamma and cost values as the main parameters, we set gamma as 0.5 and cost as 10, based on the optimal value function. The cost is set higher than general cases. To show the feasibility of the idea proposed in this paper, we compared the proposed method with MLE (Maximum Likelihood Estimation), Term Frequency, and Collective Intelligence method. Overall accuracy and was used as the metric. As a result, the overall accuracy of the proposed method was 92.41% of illegal loan advertisement and 77.75% of illegal visit sales, which is apparently superior to that of the Term Frequency, MLE, etc. Hence, the result suggests that the proposed method is valid and usable practically. In this paper, we propose a framework for crisis management caused by abnormalities of unstructured data sources such as SNS. We hope this study will contribute to the academia by identifying what to consider when applying the SVM-like discrimination algorithm to text analysis. Moreover, the study will also contribute to the practitioners in the field of brand management and opinion mining.