Detecting Credit Loan Fraud Based on Individual-Level Utility (개인별 유틸리티에 기반한 신용 대출 사기 탐지)
-
- Journal of Intelligence and Information Systems
- /
- v.18 no.4
- /
- pp.79-95
- /
- 2012
As credit loan products significantly increase in most financial institutions, the number of fraudulent transactions is also growing rapidly. Therefore, to manage the financial risks successfully, the financial institutions should reinforce the qualifications for a loan and augment the ability to detect a credit loan fraud proactively. In the process of building a classification model to detect credit loan frauds, utility from classification results (i.e., benefits from correct prediction and costs from incorrect prediction) is more important than the accuracy rate of classification. The objective of this paper is to propose a new approach to building a classification model for detecting credit loan fraud based on an individual-level utility. Experimental results show that the model comes up with higher utility than the fraud detection models which do not take into account the individual-level utility concept. Also, it is shown that the individual-level utility computed by the model is more accurate than the mean-level utility computed by other models, in both opportunity utility and cash flow perspectives. We provide diverse views on the experimental results from both perspectives.
This paper analyzes retailers' purchasing patterns of fruits and vegetables and the problems with purchasing from agricultural product wholesale markets. While large-scale retailers purchase fruits and vegetables from various sources, medium and small-scale retailers and food service companies buy them mostly from agricultural product wholesale markets. The retailers point out the problems with purchasing from agricultural product wholesale markets as a lack of quality uniformity, not sufficient cooling storage facilities, not sufficient space for shipping area, high distribution cost, unnecessary price fluctuation, and etc. In order to enhance the linkage with retailers, agricultural product wholesale markets, first of all, have to adopt more flexible trading methods such as private treaty besides auctions which are exclusively legitimate trading methods in the market. Necessary are enlargement of jobbers' operating scale, securing shipping space for retailers, adoption of inspection service, introduction of methods to stabilize auction prices, saving of loading and unloading costs, implementation of marketing strategies.
From environmental point of view, the foreign exchange crisis has motivated the Government to make the positive promoting policy for holding the foreign currency, leading to a series of small companies' bankruptcy due to foreign distribution companies' advance into our country, creating a new consuming culture. Though inaugurations have been vividly in progress in the aftermath of recession, reduced staffs and arranged layoff, their way gives priority to the reduced frame of the existing method rather tham the development or improvement of a new distribution. It is difficult to attain the sales goal unless a marketing analysis is not properly made, due to store managers' lack in expertism of management. In view of culture, the change of retail stores is imperative at the point that the type of consumers' purchase is rapidly changing and a more positive business system is needed. preventing an opportunistic loss of management through the analysis of outcome such as consumer management, sales management and account management by using computers. In view of design. the display in sale is to interpret products more charmingly, and should make interpretation accurately by selecting an important theme. For this, taking the store for valuables for instance. the progress on the effective foundation and store dinic business by presenting the design blue print can be made, and the strategy coping with the foreign distribution market's rush into Korea can be established. through the advanced store management.
한국농어촌공사 산하의 농업용저수지 중 3786개소에 대한 수질조사를 '19년도에 실시한 결과, TOC 기준 4등급 초과 저수지 비율은 약 20%로써, 도심 근교 저수지에서 녹조현상 빈발로 인해 수질, 악취, 미관 등의 환경문제 개선 민원이 다수 발생하고 있다. 현재 녹조 발생 사후관리를 위해 주로 사용되고 있는 대형 조류제거선은 저수심 수변부에서의 적용성에 한계가 있고, Al 기반의 응집제를 사용하여 조류를 수거해서 폐기하고 있는 실정이다. (주)이엔이티는 농어촌연구원, (주)코레드, (주)삼호인넷과 함께 호소나 정체하천의 수변지역에 적용될 수 있는 저에너지형 유해조류 포집시스템 개발과, 수거된 조류부산물을 무독화하여 농업재료로 재활용하는 방안을 연구하고 있다. 저수지나 정체수역의 녹조는 바람, 수면유동 등에 의해 수변에 집적되는 특성이 있어, 인공지능 기술로 녹조현상을 감시하여 조류 밀집구간에 접근할 수 있는 자율이동식 수상이동장치를 개발 중이다. 수상이동장치는 조류포집장치를 탑재하기 위한 부력체, 원격 운전이 가능한 무인항법장치, 수변식생대 및 저수심지역 이동을 고려한 수차방식 추진체, 전체 장치의 전원 공급을 위한 고성능 배터리 등으로 구성하여 상세 도면 설계를 진행하고 있다. 조류포집장치에는 표층에 주로 분포하는 남조류를 선택 흡입하는 포집 부표를 적용하였고, Al계 응집제 사용을 배제한 분리막 실험을 통해 침지형 막분리조 및 가압형 농축조를 설계하였다. 유해조류 포집 및 농축은 수상에서 이동체에 탑재하여 이뤄지고, 육상에서는 자원 회수가 가능하도록 회분식 응집공정으로 구분하였다. 조류 밀집지역에서 수거된 조류의 무독화 및 농업재료 자원화 타당성 평가를 위해 특용 버섯균주를 활용한 시료별 분석항목을 선정하고 실험 매트릭스에 따라 실증실험을 수행하였다. 수거조류를 전처리하여 성분 및 발열량을 분석하고 버섯재배 전후의 마이크로시스틴 독소(LR, RR, LR)를 포함한 성분 분석을 수행하여, 고체연료, 비료 및 사료로 활용방안을 검토하였다. 무인자율이동 조류포집장치는 실증화 규모로 제작하여 기선정된 테스트베드에서 현장적용성 평가를 수행할 예정이다. 본 연구를 통해 개발된 유해조류 포집 시스템은 기존의 녹조제거 방안을 보완하여 정체수역의 생태계 복원 및 친수공간의 환경개선 등에 적용되며, 무독화가 입증된 유해조류의 농업재료 자원화 기술은 고부가 상품 개발 및 환경폐기물 감축에 활용될 것이다.
Recommender system has become one of the most important technologies in e-commerce in these days. The ultimate reason to shop online, for many consumers, is to reduce the efforts for information search and purchase. Recommender system is a key technology to serve these needs. Many of the past studies about recommender systems have been devoted to developing and improving recommendation algorithms and collaborative filtering (CF) is known to be the most successful one. Despite its success, however, CF has several shortcomings such as cold-start, sparsity, gray sheep problems. In order to be able to generate recommendations, ordinary CF algorithms require evaluations or preference information directly from users. For new users who do not have any evaluations or preference information, therefore, CF cannot come up with recommendations (Cold-star problem). As the numbers of products and customers increase, the scale of the data increases exponentially and most of the data cells are empty. This sparse dataset makes computation for recommendation extremely hard (Sparsity problem). Since CF is based on the assumption that there are groups of users sharing common preferences or tastes, CF becomes inaccurate if there are many users with rare and unique tastes (Gray sheep problem). This study proposes a new algorithm that utilizes Social Network Analysis (SNA) techniques to resolve the gray sheep problem. We utilize 'degree centrality' in SNA to identify users with unique preferences (gray sheep). Degree centrality in SNA refers to the number of direct links to and from a node. In a network of users who are connected through common preferences or tastes, those with unique tastes have fewer links to other users (nodes) and they are isolated from other users. Therefore, gray sheep can be identified by calculating degree centrality of each node. We divide the dataset into two, gray sheep and others, based on the degree centrality of the users. Then, different similarity measures and recommendation methods are applied to these two datasets. More detail algorithm is as follows: Step 1: Convert the initial data which is a two-mode network (user to item) into an one-mode network (user to user). Step 2: Calculate degree centrality of each node and separate those nodes having degree centrality values lower than the pre-set threshold. The threshold value is determined by simulations such that the accuracy of CF for the remaining dataset is maximized. Step 3: Ordinary CF algorithm is applied to the remaining dataset. Step 4: Since the separated dataset consist of users with unique tastes, an ordinary CF algorithm cannot generate recommendations for them. A 'popular item' method is used to generate recommendations for these users. The F measures of the two datasets are weighted by the numbers of nodes and summed to be used as the final performance metric. In order to test performance improvement by this new algorithm, an empirical study was conducted using a publically available dataset - the MovieLens data by GroupLens research team. We used 100,000 evaluations by 943 users on 1,682 movies. The proposed algorithm was compared with an ordinary CF algorithm utilizing 'Best-N-neighbors' and 'Cosine' similarity method. The empirical results show that F measure was improved about 11% on average when the proposed algorithm was used