• Journal of the Korean Data and Information Science Society
• /
• 제24권2호
• /
• pp.267-275
• /
• 2013

데이터 마이닝 기법들 중에서도 연관성 규칙은 가장 최근에 개발된 기법으로 대용량 데이터베이스에서 각 항목들 간의 관련성을 찾아내며, 두 항목간의 관계를 명확히 수치화함으로써 두 개 이상의 항목간의 관련성을 표시하여 주기 때문에 현장에서 직접 적용이 가능하다. 일반적으로 연관성 규칙 생성 여부를 판단할 때, 각 항목간의 연관성을 반영하는 기준인 지지도, 신뢰도, 향상도 등의 흥미도 측도를 활용하게 된다. 실제적으로 연관성 규칙의 수를 결정하기 위해서는 이들 흥미도 측도들의 평가기준을 정하기 위해 반복적으로 조정 과정을 거쳐야 한다. 본 논문에서는 이러한 문제를 해결하기 위해 연관성 평가기준 모두를 일반적으로 많이 활용되고 있는 비선형 회귀모형에 적용하여 연관성 규칙의 수를 추정하는 방안을 강구하였다. 또한 분산팽창계수를 이용하여 다중공선성 문제를 진단하는 동시에 분산분석 결과와 수정 결정계수를 이용하여 각 모형의 기여도를 비교하여 가장 바람직한 회귀 모형을 구하였다.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2008년도 춘계 종합학술대회 논문집
• /
• pp.84-86
• /
• 2008

회사들이 정보를 효율적으로 이용할 수 있도록 제어하고 필터링하는 일을 도와주는 고객 관계 마케팅이 등장하였으며, 더 나아가 고객이 원하는 제품을 예측하고 추천해 주기 위해 데이터 마이닝을 적용하고 있다. 본 논문에서는 데이터 마이닝의 연관 규칙을 이용한 적응적 고객 관계 관리 전략을 제안하였다. 제안된 방법으로는 연관 규칙을 이용하여 후보 고객 집합으로 빈발 고객을 구성하고 연관 고객들의 규칙을 생성한다. 생성된 연관 규칙의 향상도에 따라서 하이퍼 그래프 분할을 이용하여 구매 고객들의 효율적인 특성을 분석한다. 따라서 고객들에 대한 교차 판매와 격상 판매의 전략들을 도출하게 된다.

• 한국중재학회지:중재연구
• /
• 제18권2호
• /
• pp.3-31
• /
• 2008

At its thirty-ninth session(New York, 19 June - 7 July 2006), United Nations Commission on International Trade Law(hereinafter referred to as the Commission) agreed to give priority to the topic of revising the UNCITRAL Arbitration Rules. From the forty-fifth through the forty-seventh session, the Working Group checked various issues based on the draft revised version of the UNCITRAL Arbitration Rules prepared by the Secretariat. At its forty-eighth session, the Working Group is going to finish its first reading of articles 38 to 41 of the draft revised version of the UNCITRAL Arbitration Rules, and to commence its second reading of the draft revised version of UNCITRAL Arbitration Rules. Korea is keen on enticing foreign direct investment into its territory. From the 1960s, Korea has concluded more than 80 BITs. Korea is making efforts to conclude FTAs with its trading partners. As of January, 2008, 3 FTAs have taken into effect with respect to Korea. According to provisions on dispute settlement found in such BITs and FTAs involving Korea, the Rules can be chosen for Investor-State Arbitration. Furthermore, the Rules is followed by the arbitration rules for domestic and international arbitrations administered by the Korean Commercial Arbitration Board. If the Commission adopts the revised version of UNCITRAL Arbitration Rules, the Rules will be able to give impact on the arbitration law and practice around the world of arbitration. That is the reason why we should keep attention to the development of the deliberations of the Working Group.

• 한국중재학회지:중재연구
• /
• 제23권4호
• /
• pp.3-27
• /
• 2013

Overriding Mandatory rules are laws that purport to apply irrespective of the law chosen by the parties to govern their contractual relations. This article examines their role and applicability in international arbitration. The overriding mandatory rules pose a complex and continuing problem for arbitrators because they put the interests of states and parties in direct competition. When a law says that arbitrators must apply it, yet the parties' contract excludes it, what should the arbitrators do? Where should their allegiance lie? The answer depends on the underlying nature of arbitration - and since that can be legitimately conceptualized in different ways, a principled approach to overriding mandatory rules seems to be impossible to provide. Nevertheless, a practical solution is required, because there were European cases in which courts voided valid arbitration agreements made, reasoning that arbitrators certainly would not apply and/or take into account its overriding mandatory rules of indemnity right granted to commercial agent and distributor in Europe. Therefore, this paper first examines status of overriding mandatory rules of another law in international litigation and then explores any possibility of application of overriding mandatory rules of another law in international commercial arbitration. With this analysis, the author reaches into a conclusion that the arbitrator should and/or take into account overriding mandatory rules of another law, yet should limit to them of the country where characteristic performance is made under the contract.

• 대한산업공학회지
• /
• 제27권1호
• /
• pp.30-36
• /
• 2001

We present a new algorithm for mining association rules in the large database. Association rules are the relationships of items in the same transaction. These rules provide useful information for marketing. Since Apriori algorithm was introduced in 1994, many researchers have worked to improve Apriori algorithm. However, the drawback of Apriori-based algorithm is that it scans the transaction database repeatedly. The algorithm which we propose scans the database twice. The first scanning of the database collects frequent length l-itemsets. And then, the algorithm scans the database one more time to construct the data structure Common-Item Tree which stores the information about frequent itemsets. To find all frequent itemsets, the algorithm scans Common-Item Tree instead of the database. As scanning Common-Item Tree takes less time than scanning the database, the algorithm proposed is more efficient than Apriori-based algorithm.

• 아동학회지
• /
• 제19권2호
• /
• pp.147-157
• /
• 1998

The purpose of this study was to investigate children's ideas about self-regulation in such situational variables as the presence of explicit rules and the domains of social rules. The subjects were 6-, 9-, and 12-year-old children (344). To assess children's ideas about self-regulation, a procedure was devised in which children were presented with stories portraying a protagonist in a conflict between an implicit or an explicit rule and a personal desire. The children were asked to make a choice for the protagonist and to give reasons for their choice. Major findings as follows: (1) There was significant difference in children's self-regulation depending on the presence of explicit rules. (2) There was significant difference in children's self-regulation depending on the domains of social rules. In situations that involved no explicit rules for behaviors, there were significant differences depending on the domains. In situations that involved explicit rules for behaviors, for 6- and 9-year-old children, there was no significant difference depending on the domains. (3) Children's use of justifications for their choice of action varied as a function of the characteristics of the social rules.

• 한국컴퓨터정보학회논문지
• /
• 제15권12호
• /
• pp.227-235
• /
• 2010

이 논문은 RFM 기법과 연관성 분석을 이용한 개인화된 전자상거래 추천 시스템을 제안한다. 제안된 전자상거래 추천시스템은 사용자의 평가 자료에 의존하지 않고 묵시적인(Implicity)방법을 이용하여 고객정보와 구매이력 정보를 기반으로 RFM(Recency, Frequency, Monetary) 기법을 이용한 고객 세분화와 교차판매(cross-sell)관계를 찾는 연관성 분석을 이용한 개선된 시스템이다. 또한 고객군별 구매특성 분석을 통하여 효율적인 마케팅 전략과 고객관계관리(CRM: Customer Relationship Management)방법을 제시한다. 현업에서 사용하는 데이터 셋을 구성하여 실험 및 평가를 통해서 효용성을 입증 및 평가하여 일대일 웹 마케팅을 실현하였다.

• 대한산업공학회지
• /
• 제32권3호
• /
• pp.242-252
• /
• 2006

Data mining is the exploration and analysis of huge amounts of data to discover meaningful patterns. One of the most important data mining problems is association rule mining. Recent studies of mining association rules have proposed a closure mechanism. It is no longer necessary to mine the set of all of the frequent itemsets and their association rules. Rather, it is sufficient to mine the frequent closed itemsets and their corresponding rules. In the past, a number of algorithms for mining frequent closed itemsets have been based on items. In this paper, we use the transaction itself for mining frequent closed itemsets. An efficient algorithm is proposed that is based on a link structure between transactions. Our experimental results show that our algorithm is faster than previously proposed methods. Furthermore, our approach is significantly more efficient for dense databases.

• 산업경영시스템학회지
• /
• 제25권1호
• /
• pp.1-8
• /
• 2002

The traditional approaches of association rule mining have relied on high support condition to find interesting rules. However, in some application such as analyzing the web page link and discovering some unusual combinations of some factors that have always caused some disease, we are interested in rules with high confidence that have very low support or need not have high support. In these cases, the traditional algorithms are not suitable since it relies on first satisfying high support. In this paper, we propose a new model, CP(Confidence Pattern)-Tree, to identify high confidence rule between 2-items without support constraint. constraint. In addition, we discuss confidence association rule between two more items without support constraint.

• 한국경영과학회지
• /
• 제27권4호
• /
• pp.29-39
• /
• 2002

The transaction tables of the existing association algorithms have two column attributes : It is composed of transaction identifier (Transaction_id) and an item identifier (item). In this kind of structure, as the volume of data becomes larger, the performance for the SQL query statements came applicable decreases. Therefore, we propose advanced association rules algorithm of n-items which can transact multiple items (Transaction_id, Item 1, Item 2…, Item n). In this structure, performance hours can be contracted more than the single item structures, because count can be computed by query of the input transaction tables. Our experimental results indicate that performance of the n items structure is up to 2 times better than the single item. As a result of this paper, the proposed algorithm can be applied to internet shopping, searching engine and etc.