• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.111-126
• /
• 2020

Most industries have recently become aware of the importance of customer lifetime value as they are exposed to a competitive environment. As a result, preventing customers from churn is becoming a more important business issue than securing new customers. This is because maintaining churn customers is far more economical than securing new customers, and in fact, the acquisition cost of new customers is known to be five to six times higher than the maintenance cost of churn customers. Also, Companies that effectively prevent customer churn and improve customer retention rates are known to have a positive effect on not only increasing the company's profitability but also improving its brand image by improving customer satisfaction. Predicting customer churn, which had been conducted as a sub-research area for CRM, has recently become more important as a big data-based performance marketing theme due to the development of business machine learning technology. Until now, research on customer churn prediction has been carried out actively in such sectors as the mobile telecommunication industry, the financial industry, the distribution industry, and the game industry, which are highly competitive and urgent to manage churn. In addition, These churn prediction studies were focused on improving the performance of the churn prediction model itself, such as simply comparing the performance of various models, exploring features that are effective in forecasting departures, or developing new ensemble techniques, and were limited in terms of practical utilization because most studies considered the entire customer group as a group and developed a predictive model. As such, the main purpose of the existing related research was to improve the performance of the predictive model itself, and there was a relatively lack of research to improve the overall customer churn prediction process. In fact, customers in the business have different behavior characteristics due to heterogeneous transaction patterns, and the resulting churn rate is different, so it is unreasonable to assume the entire customer as a single customer group. Therefore, it is desirable to segment customers according to customer classification criteria, such as loyalty, and to operate an appropriate churn prediction model individually, in order to carry out effective customer churn predictions in heterogeneous industries. Of course, in some studies, there are studies in which customers are subdivided using clustering techniques and applied a churn prediction model for individual customer groups. Although this process of predicting churn can produce better predictions than a single predict model for the entire customer population, there is still room for improvement in that clustering is a mechanical, exploratory grouping technique that calculates distances based on inputs and does not reflect the strategic intent of an entity such as loyalties. This study proposes a segment-based customer departure prediction process (CCP/2DL: Customer Churn Prediction based on Two-Dimensional Loyalty segmentation) based on two-dimensional customer loyalty, assuming that successful customer churn management can be better done through improvements in the overall process than through the performance of the model itself. CCP/2DL is a series of churn prediction processes that segment two-way, quantitative and qualitative loyalty-based customer, conduct secondary grouping of customer segments according to churn patterns, and then independently apply heterogeneous churn prediction models for each churn pattern group. Performance comparisons were performed with the most commonly applied the General churn prediction process and the Clustering-based churn prediction process to assess the relative excellence of the proposed churn prediction process. The General churn prediction process used in this study refers to the process of predicting a single group of customers simply intended to be predicted as a machine learning model, using the most commonly used churn predicting method. And the Clustering-based churn prediction process is a method of first using clustering techniques to segment customers and implement a churn prediction model for each individual group. In cooperation with a global NGO, the proposed CCP/2DL performance showed better performance than other methodologies for predicting churn. This churn prediction process is not only effective in predicting churn, but can also be a strategic basis for obtaining a variety of customer observations and carrying out other related performance marketing activities.

• Journal of Korean Society of Forest Science
• /
• v.74 no.1
• /
• pp.47-55
• /
• 1986

During the past 4 years, I have made a careful analysis of the present rotating system of hunting areas, on the one hand, by asking a group of hunters to fill out a questionnaire, and on the other hand, by referring to the written documents on the subject. And, as a result, it is concluded that this system, by varying the hunting grounds each year, contains in itself several problems as follows. 1. The hunters find it quite inconvenient to use a different hunting ground year after year and they also complain that the present hunting ground charge is more than it is worth. Therefore, it is expected that the number of hunters will explosively increase in the future with the betterment of hunting conditions. 2. The hunters have almost no information about game and they are, as a whole, lacking in the ethics of hunting. 3. The allotment of time in hunting training courses is not so sufficient that it is next to impossible to improve the quality of hunters. 4. As a rule, the population density of wildlife is so sparse that it falls short of the proper standard of it. 5. The present hunting system does not seem to contribute to the advancement of tourism. 6. It is absolutely necessary to make a general survey of the situation of wildlife for the legal protection of it. Besides, the interests of hunters are so closely tied up with those of farmers and foresters that dreastic measures should be taken to settle their conflicting differences. For the purpose of solving the above-mentioned problems and at the same time, of developing sound hunting practices in the long run, I hereby make two suggestions. 1. The Establishment of the Hunting License Test System It is desirable to issue a license to a prospective hunter after he has met a special qualification and then passed a test so that he may have bits of information needed for his hunting activities. 2. The Introduction of The Revier System The fundamental concept of this system is based on the assumption that the private landowner should reserve a right to the pursuit of game and take responsibility for wildlife management.

• Journal of Environmental Policy
• /
• v.9 no.2
• /
• pp.3-19
• /
• 2010

Anyang-cheon(stream) runs through southern metropolitan area of Seoul to Han-river in Korea. Due to fast growth of Seoul, the water quality and quantity problems in Anyang-cheon have occurred. To cope with the problems, the Integrated Watershed Management program for Anyang-cheon was adopted and a KRW 26.1 billion (USD 21.8 million) pilot project (construction of 4 facilities such as reservoir) is suggested for 4 sub-watersheds of Anyang-cheon, which cost will be shared by the 12 local governments (LG). Three cost division schemes are compared. By Scheme 1, if the cost is borne by the LG in a watershed where the facilities are constructed (no cost division scheme), the LG in I is to bear 0.58% of the total construction cost, LG in watershed II 29.54%, LG in IV 0%, LG in V 69.88%. In particular, LG in IV in this scheme bears no cost because no facility is constructed, even though watershed IV is the major beneficiary of the facility construction. Scheme 2 is to share the cost by length of streams in each sub-watershed and the suggested cost share for each sub-watershed is 13.76% by I, 7.34% by II, 45.87% by IV, and 33.03% by V. However, this cost division scheme is fair only under the false assumption that the bargaining powers of group of LGs are identical. To suggest a better and fair division rule, Shapley Value, a cooperative game solution, is used to suggest Scheme 3. In Scheme 3, Shapley Value measures the summation of average marginal contribution of each player in all possible coalitions as cost division scheme and is known to provide a fair division considering bargaining power. In the context of Anyang-cheon, LGs in upper stream have superior bargaining position. The result suggests the cost division is fair under Scheme 3, when the cost shares are 0.29% by I, 14.77% by II, 50% by IV, and 34.94% by V, respectively.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.1
• /
• pp.56-63
• /
• 2007

In this paper, an eye tracking method is presented using a neural network (NN) and mean-shift algorithm that can accurately detect and track user's eyes under the cluttered background. In the proposed method, to deal with the rigid head motion, the facial region is first obtained using skin-color model and con-nected-component analysis. Thereafter the eye regions are localized using neural network (NN)-based tex-ture classifier that discriminates the facial region into eye class and non-eye class, which enables our method to accurately detect users' eyes even if they put on glasses. Once the eye region is localized, they are continuously and correctly tracking by mean-shift algorithm. To assess the validity of the proposed method, it is applied to the interface system using eye movement and is tested with a group of 25 users through playing a 'aligns games.' The results show that the system process more than 30 frames/sec on PC for the $320{\times}240$ size input image and supply a user-friendly and convenient access to a computer in real-time operation.

• Journal of the Korean Society of School Health
• /
• v.15 no.1
• /
• pp.93-105
• /
• 2002

This study was aimed at identifying on the state and knowledge toward smoking and passive smoking in middle school students. The data were collected from 6th. to 18th. August, 2001. Subject were 125 middle school students who were participated in the Smoking Cessation Program of S Health Agency in Busan. The collected data were analyzed by SPSS program for frequency, percent, mean, and chi-square test. The smoking related state and attitude of subjects were as follows; the nurmber of the smoking students are 10(8.0 %) at present, 19(15.2 %) at past experience, 53(42.4 %) having at present smoking friends, 73(58.4 %) having at present smoking family. Also the smoking starting time of present or past smoking experience was the middle school; 12(9.6 %) and elementary school; 11(8.8 %). They started because of the peer group members; 12(9.6 %), curiosity; 8(6.4 %), and looking good; 7(5.6 %). The passive smoking related state and attitude of subjects were as follows; the number of the passive smoking aware rates are very well level; 71(56.8 %), well level; 54(43.2 %). The exposed experience to passive smoking was always; 38(30.4 %), sometimes; 86(68.8 %), not experience; 1(0.8 5). The place of exposure to passive smoking was game rooms; 67(53.6 %), house; 30(24.0 %), fast food place or cafeteria; 10(8.0 %), and street or in a vehicle ; 3(2.4 %). The main smoker to passive smoking exposure was unknown person; 61(48.8 %), grand parents or parents; 43(34.4 %), brothers or friends; 8(6.4 %), teachers; 4(3.2 %). The chief complant of passive smoking exposure was dyspnea; 36(28.8 %), coughing; 34(27.2 5), dizziness; 21(16.8 %), no symptom; 18(14.4 %). The mostly affected smoker to passive smoking exposure was parents; 52(41.6 %), brothers or friends; 48(38.4 %). The health affected perception to passive smoking exposure was very affected; 109(87.2 %), not affected; 3(2.4 %). In conclusion, it can be well recognized that considerable number of middle school students is exposed to the passive smoking in their homes and by unknown persons, but, their knowledge and attitude toward the exposure to passive smoking is not effective. Therefore, it is hoped that regular smoking education program at school and restriction campaign in home and the public place is necessary.

• Journal of Families and Better Life
• /
• v.20 no.5
• /
• pp.149-166
• /
• 2002

In this study, 1 have analyzed the state of the use of information technology by the at-risk children who are residing in Husan metropolitan area. The ultimate goal of this study is to help ensure the healthy development of the children and improve the quality of their lives in this information-oriented society. For this research, 1 surveyed 183 children living in an institution or a low-income family in Busan metropolitan area. The survey questionnaire was designed to obtain information on the respondents, socio-demographic characteristics, computer-related conditions of the immediate and social environments, patterns of computer and Internet use, their experience and degree of so called, Net-generation syndrome, Internet addiction disorder, changes in social and familial life caused by Internet use, and exposure to pornographic materials. The results show that 95.9 % of at-risk children in Husan own a computer, 60.9 % of those computers being Pentium Ⅲ. A majority of the children (74.9 %) are connected to Internet at a high-speed, using such devices as LAN, ADSL or cables. About seventy-six percent of the children have used a PC and Internet less than two years. In other words, a majority of them have not used those for a long period of time. The main results of the research are summarized in the following: There is a significant difference among at-risk children in terms of experiences in computer and Internet use according to their grade levels. There is a gender difference in the amount of time spent on computer and Internet. Boys spend more time every week on computer and Internet than girls do. There is a significant difference in the pattern of computer and Internet use, according to the type of their risk, and grade level. The so-called 'Net Generation Syndrome' is not serious in this group. A majority of the at-risk children think that Internet is more interesting than TV. They hardly shop on Internet, and they don think the advertisements on Internet are a serious problem. Also, unlike many people assumptions, their desire to communicate through on-line chatting was very low. They do not tend to buy computer game programs, and Internet Addiction Disorder was not pronounced among them. The at-risk children rarely had an exposure to pornographic materials in the cyber space. However, the exposure was more frequent for institutionalized children than children in low-income families. These results point to a need for a policy to improve the welfare of at-risk children and guarantee their right to information.

• Journal of Korean Society of Transportation
• /
• v.21 no.2
• /
• pp.71-82
• /
• 2003

The shortest path problems(SPP) are critical issues in the military logistics such as the simulation of the War-Game. However, the existing SPP has two major drawbacks, one is its accuracy of solution and the other is for only one solution with focused on just link cost in the military transportation planning models. In addition, very few previous studies have been examined for the multi-shortest path problems without considering link capacity reflecting the military characteristics. In order to overcome these drawbacks, it is necessary to apply the multi-shortest paths algorithm reflecting un-expected military incidents. This study examines the multi-shortest paths in the real networks using Shier algorithm. The network contains both military link capacity and time-based cost. Also, the modes are defined as a platoon(group) rather than unit which is used in most of previous studies in the military logistics. To verify the algorithm applied in this study. the comparative analysis was performed with various sizes and routes of network which compares with Dijkstra algorithm. The major findings of this study are as follows ; 1) Regarding the unique characteristics of the military transportation plan, Shier algorithm, which is applied to this study, is more realistic than Dijkstra algorithm. Also, the time based concept is more applicable than the distance based model in the military logistics. 2) Based on the results from the various simulations of this study the capacity-constraint sections appeared in each scenarios. As a consequence, the alternatives are necessary such as measures for vulnerable area, improvement of vehicle(mode), and reflection of separated-marching column in the military manuals. Finally. the limits and future research directions are discussed : 1) It is very hard to compare the results found in this study. which is used in the real network and the previous studies which is used in arbitrary network. 2) In order to reflect the real military situations such as heavy tanks and heavy equipment vehicles. the other constraints such as the safety load of bridges and/or the height of tunnels should be considered for the future studies.

• Journal of Service Research and Studies
• /
• v.7 no.4
• /
• pp.151-164
• /
• 2017

This study aims to explore the effect of quality factors and learning styles on users' satisfaction in the use of business simulation tools in business education. For this purpose, statistical methods such as reliability test, factor analysis, ANOVA, regression analysis were carried out using the survey data from university students. The quality factors of education using simulation were classified into contents, education environment, interpersonal activities, and instructor support while learning styles were classified into proactive, self-directed, environmental-dependent, and passive styles. The results showed that each quality factors of education using business simulation had a strong positive effect on user satisfaction. Proactive and environment-dependent group had higher satisfaction than other groups. Learning styles had moderating effects on the quality-satisfaction relationship, and the direction and degree varied depending on the quality factors and learning styles. Theoretical and practical implications were drawn from these findings.

• Journal of Intelligence and Information Systems
• /
• v.14 no.3
• /
• pp.59-76
• /
• 2008

In this paper, we propose an agent architecture called L-CAA that is quite effective in real-time dynamic environments. L-CAA is an extension of CAA, the behavior-based agent architecture which was also developed by our research group. In order to improve adaptability to the changing environment, it is extended by adding reinforcement learning capability. To obtain stable performance, however, behavior selection and execution in the L-CAA architecture do not entirely rely on learning. In L-CAA, learning is utilized merely as a complimentary means for behavior selection and execution. Behavior selection mechanism in this architecture consists of two phases. In the first phase, the behaviors are extracted from the behavior library by checking the user-defined applicable conditions and utility of each behavior. If multiple behaviors are extracted in the first phase, the single behavior is selected to execute in the help of reinforcement learning in the second phase. That is, the behavior with the highest expected reward is selected by comparing Q values of individual behaviors updated through reinforcement learning. L-CAA can monitor the maintainable conditions of the executing behavior and stop immediately the behavior when some of the conditions fail due to dynamic change of the environment. Additionally, L-CAA can suspend and then resume the current behavior whenever it encounters a higher utility behavior. In order to analyze effectiveness of the L-CAA architecture, we implement an L-CAA-enabled agent autonomously playing in an Unreal Tournament game that is a well-known dynamic virtual environment, and then conduct several experiments using it.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.31 no.2
• /
• pp.203-221
• /
• 2020

This study closely analyzed changes in the educational environment and changes in the needs of children's and young people's reading culture programs, which are directly beneficiaries of the promotion of reading culture as they enter the fourth industrial revolution. It also comprehensively evaluated the reading culture promotion project for children and adolescents promoted by the National Children and Youth Library and proposed a reading culture promotion project that meets the needs of the smart era. This study investigated the cases of various domestic and foreign reading culture promotion projects to divulge trends. The authors invited experts from public libraries and school libraries with experience of the reading culture promotion projects and performed Focus Group Interviews (FGI). The authors evaluated individual reading culture program based on the PDCA method (Plan, Do, Check, Act). Based on the data obtained through case studies and expert evaluations, the development plan of reading culture promotion project and the strategy of promoting new projects to be pursued in the National Children and Youth Library were presented. By gathering the results of the research, 'Interactive e-book making platform production / distribution business', 'Game-type reading program production / distribution business', 'Habruta reading culture dissemination project using backward learning method', 'Youth coding branding "Teen-Start -Up"' were proposed as new services.