• Communications for Statistical Applications and Methods
• /
• 제22권5호
• /
• pp.487-494
• /
• 2015

A calculation of the Kullback-Leibler information of consecutive order statistics is complicated because it depends on a multi-dimensional integral. Park (2014) discussed a representation of the Kullback-Leibler information of the first r order statistics in terms of the hazard function and simplified the r-fold integral to a single integral. In this paper, we first express the Kullback-Leibler information in terms of the reversed hazard function. Then we establish a generalized result of Park (2014) to an arbitrary consecutive order statistics. We derive a single integral form of the Kullback-Leibler information of an arbitrary block of order statistics; in addition, its relation to the Fisher information of order statistics is discussed with numerical examples provided.

• Fashion, Industry and Education
• /
• 제16권1호
• /
• pp.19-35
• /
• 2018

This study explores the effect of information direction and order of cosmetics power bloggers on consumer responses. A total of 488 undergraduate students participated in experiments with mock-up stimuli of sunscreen product reviews by power bloggers. The study was conducted with four stimuli of product review posts (i.e., positive reviews only, positive-negative reviews in order, negative-positive reviews in order, negative reviews only) of the power bloggers. The results showed a significant difference in consumer responses according to information direction and order of product reviews of the power bloggers. Specifically, negative reviews were considered more objective and more useful than positive reviews were. However, positivity of reviews is crucial in generating more positive attitudes toward products, greater purchase intention, and greater word-of-mouth intention. In regard to information order, the negative-positive reviews generated more positive attitudes toward the product and greater purchase intention than did the positive-negative reviews, emphasizing the importance of ending product reviews with positive information so as to create positive responses. Referring to the findings, power bloggers and marketers using bloggers as a promotional tool would benefit by carefully designing information content in consideration of an appropriate direction and order of information to better fit their purpose.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.89-92
• /
• 2002

As the use of Internet being generalized, ordering system can be easily achieved on the Web so that the direct sailing system is replaced the various types of Built-To-Order system. It is important to give the up-to-date information to the end-user in order to build the Built-To-Order system. Recently, the way of providing information is updating the product related information continuously. In this study, we provide the method that can be streamlined Product Data Management System which manages a creation and update for product information into the direct BTO system in order to achieve the newest information. This methodology is not only transferring the information but also processing the information in an appropriate form. So this paper is going to cover the various point of view of information processing.

• 산업공학
• /
• 제18권2호
• /
• pp.148-157
• /
• 2005

The manufacturing industry with Make-to-Order production system is difficult to decide the standard information for the product and the demand is variable to estimate. In this paper, we concerned with the process planning method using data mining in the manufacturing industry with Make-to-Order environment. The subject of our study is the industry transformer plant which is received an diverse order of customer and then produced the product. Currently, process planning method is classified the standard information by hand based on the acquired knowledge through the experience. The standard information stored the various information, such as work sequence, time and so on. This process planning method needs an experts which possesses the field experience for several years. For the product specification which is varied in each order, current process planning method is not efficient due to need many times To solve this problem, we extract the information using data mining process for each processing time, and then construct the knowledge base. We propose a method which is the process planning of the industry transformer product in Make-to-Order environment using the knowledge base.

• 한국도로학회논문집
• /
• 제15권1호
• /
• pp.135-141
• /
• 2013

PURPOSES: In this study, as part of an effort to develop HUD for public transit, it is proposed that the decision of order priority of contents which will be disposed to bus drivers through HUD for public transit using AHP(Analytic Hierarchy Process) technique. METHODS: In AHP analysis method brainstorming, factor analysis, hierarchical structuring, and weighting analysis were performed by applying a classical analysis method. RESULTS: By the result of analysis it is shown that unlike car drivers, bus drivers prefer information related to bus intervals, bus stop, and door open and close to information related to vehicle running. Also, bus stop information and bus interval information were ranked as first and second place in order priority of HUD contents for public transit by experts. CONCLUSIONS: This method of selecting order priority of HUD contents for public transit can provide a basic foundation for selecting order priority of traffic information contents as well as other HUD contents.

• Communications for Statistical Applications and Methods
• /
• 제6권2호
• /
• pp.397-402
• /
• 1999

We first derive the Fisher information identity in order statistics in terms of the hazard rate by considering the Fisher information identity in terms of the hazard rate (Efron and Johnstone, 1990). Then we use the identity and show an interesting and useful result that some identities and recurrence relations for the Fisher information in order statistics can be directly obtained from those between the c.d.f.s of order statistics.

• 지능정보연구
• /
• 제28권4호
• /
• pp.157-177
• /
• 2022

투자자들은 증권회사가 제공하는 시세표인 Limit Order Book 정보를 통해 국내외 투자자들이 제출하는 주문 정보를 실시간으로 파악하면서 거래에 참여하고 있다. Limit Order Book에 실시간으로 공개되고 있는 주문 정보가 주가 예측에서 유용성이 있을까? 본 연구는 장 중 투자자들의 매수와 매도 주문이 어느 한쪽으로 쏠리면서 주문 불균형이 나타나는 경우 미래 주가 등락의 예측 변수로서 유의성이 있는지를 분석하는 것이다. 분류 알고리즘을 이용하여 주문 불균형 정보의 당일 종가 등락에 대한 예측 정확도를 높이고, 예측 결과를 이용한 데이트레이딩 전략을 제안하며 실증분석을 통해 투자 성과를 분석한다. 자료는 2004년 1월 19일부터 2022년 6월 30일까지의 4,564일 동안의 코스피200 주가지수선물 5 분 봉 주가를 분석하였다. 실증분석 결과는 다음과 같다. 첫째, 총매수 주문량과 총매도 주문량의 불균형 정도로 측정하는 주문 불균형지수와 주가는 유의적 상관성을 보인다. 둘째, 주문 불균형 정보는 당일 종가까지의 미래 주가 등락에 대해서도 유의적인 영향력이 나타났다. 셋째, 주문 불균형 정보를 이용한 당일 종가 등락의 예측 정확도는 Support Vector Machines 알고리즘이 54.1%로 가장 높게 나타났다. 넷째, 하루 중 이른 시점에서 측정한 주문 불균형지수가 늦은 시점에서 측정한 주문 불균형지수보다 예측 정확성이 더 높았다. 다섯째, 종가 등락 예측 결과를 이용한 데이트레이딩 전략의 투자 성과는 비교모형의 투자 성과보다 높게 나타났다. 여섯째, 분류 알고리즘을 이용한 투자 성과는 K-Nearest Neighbor 알고리즘을 제외하면 모두 비교모형보다 총수익 평균이 높게 나타났다. 일곱째, Logistic Regression, Random Forest, Support Vector Machines, XGBoost 알고리즘의 예측 결과를 이용한 데이트레이딩 전략의 투자 성과는 수익성과 위험성을 동시에 평가하는 샤프비율에서도 비교모형보다 높은 결과를 보여주었다. 본 연구는 Limit Order Book 정보 중 총매수 주문량과 총매도 주문량 정보의 경제적 가치가 존재함을 밝혔다는 점에서 기존의 연구와 학술적 차별점을 갖는다. 본 연구의 실증분석 결과는 시장 참여자들에게 투자 전략적 측면에서 함의가 있다고 판단된다. 향후 연구에서는 최근 활발히 연구가 진행되고 있는 딥러닝 모형 등으로의 확장을 통해 주가 예측의 정확도를 높임으로써 데이트레이딩 투자전략의 성과를 개선할 필요가 있다.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2004년도 춘계공동학술대회 논문집
• /
• pp.636-647
• /
• 2004

The objective of this paper is to provide an improved reorder decision policy for general multi-echelon distribution systems utilizing the shared stock information. It has been known that traditional reorder policies sometimes show poor performance in distribution systems. Thus, in our previous research we introduced the order risk policy which utilizes the shared stock information more accurately for the 2-echelon distribution system and proved the optimality. However, since the real world supply chain is generally composed with more than 2 echelons, we extend the order risk policy for the general multi-echelon systems. Since the calculation of the exact order risk value for general multi-echelon systems is very complex, we provide two approximation methods for the real-time calculation. Through the computational experiment comparing the order risk policy with the existing policies under various conditions, we show the performance of the order risk policy and analyze the value of the shared stock information varying with the characteristics of the supply chain.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2003년도 추계학술대회 및 정기총회
• /
• pp.159-165
• /
• 2003

The objective of this paper is to provide an improved reorder decision policy for general multi-echelon distribution systems utilizing the shared stock information. Since it has been known that traditional reorder policies sometimes show poor performance in distribution systems, in our previous research we introduced the order risk policy which utilizes the shared stock information more accurately f3r the 2-echelon distribution system and proved the optimality. However, since the real world supply chain is generally composed with more than 2 echelons, we extend the order risk policy for the general multi-echelon systems. Since the calculation of the exact order risk value fur general multi-echelon systems is very complex, we provide two approximation methods. Through the computational experiment comparing the order risk policy with the existing policies under various conditions, we show the performance of the order risk policy and analyze the value of the shared stock information varying with the characteristics of the supply chain.

• 산업공학
• /
• 제17권3호
• /
• pp.359-374
• /
• 2004

The objective of this paper is to provide an improved reorder decision policy for general multi-echelon distribution systems utilizing the shared stock information. It has been known that traditional reorder policies sometimes show poor performance in distribution systems. Thus, in our previous research we introduced the order risk policy which utilizes the shared stock information more accurately for the 2- echelon distribution system and proved the optimality. However, since the real world supply chain is generally composed with more than 2 echelons, we extend the order risk policy for the general multi-echelon systems. Since the calculation of the exact order risk value for general multi-echelon systems is very complex, we provide two approximation methods for the real-time calculation. Through the computational experiment comparing the order risk policy with the existing policies under various conditions, we show the performance of the order risk policy and analyze the value of the shared stock information varying with the characteristics of the supply chain.