• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.99-120
• /
• 2010

Due to the wide spread of customers' frequent access of non face-to-face services, there have been many attempts to improve customer satisfaction using huge amounts of data accumulated throughnon face-to-face channels. Usually, a call center is regarded to be one of the most representative non-faced channels. Therefore, it is important that a call center has enough agents to offer high level customer satisfaction. However, managing too many agents would increase the operational costs of a call center by increasing labor costs. Therefore, predicting and calculating the appropriate size of human resources of a call center is one of the most critical success factors of call center management. For this reason, most call centers are currently establishing a department of WFM(Work Force Management) to estimate the appropriate number of agents and to direct much effort to predict the volume of inbound calls. In real world applications, inbound call prediction is usually performed based on the intuition and experience of a domain expert. In other words, a domain expert usually predicts the volume of calls by calculating the average call of some periods and adjusting the average according tohis/her subjective estimation. However, this kind of approach has radical limitations in that the result of prediction might be strongly affected by the expert's personal experience and competence. It is often the case that a domain expert may predict inbound calls quite differently from anotherif the two experts have mutually different opinions on selecting influential variables and priorities among the variables. Moreover, it is almost impossible to logically clarify the process of expert's subjective prediction. Currently, to overcome the limitations of subjective call prediction, most call centers are adopting a WFMS(Workforce Management System) package in which expert's best practices are systemized. With WFMS, a user can predict the volume of calls by calculating the average call of each day of the week, excluding some eventful days. However, WFMS costs too much capital during the early stage of system establishment. Moreover, it is hard to reflect new information ontothe system when some factors affecting the amount of calls have been changed. In this paper, we attempt to devise a new model for predicting inbound calls that is not only based on theoretical background but also easily applicable to real world applications. Our model was mainly developed by the interactive decision tree technique, one of the most popular techniques in data mining. Therefore, we expect that our model can predict inbound calls automatically based on historical data, and it can utilize expert's domain knowledge during the process of tree construction. To analyze the accuracy of our model, we performed intensive experiments on a real case of one of the largest car insurance companies in Korea. In the case study, the prediction accuracy of the devised two models and traditional WFMS are analyzed with respect to the various error rates allowable. The experiments reveal that our data mining-based two models outperform WFMS in terms of predicting the amount of accident calls and fault calls in most experimental situations examined.

• Korean Journal of Schizophrenia Research
• /
• v.19 no.1
• /
• pp.10-16
• /
• 2016

Objectives : This article aims to describe the development of smartphone application for the case management of patients with schizophrenia. Methods : Gwangju Bukgu-Community Mental Health Center developed and launched a smartphone application (HYM) for cognitive-behavioral case management and symptom monitoring. The development of the application involved psychiatrists, nurses, social workers, psychologists, and software technicians from a software development company (Goosl Corp.). Results : The HYM application for clients includes six main modules including Thought record, Symptom record, Daily life record, Official notices, Communication, and Scales. The key module is the 'Thought Record' for self-directed cognitive-behavioral treatment (CBT). When the client writes and sends the self-CBT sheet to the case manager, the latter receives a notification and can provide feedback in real time. 'Communication' and 'Official notices' are useful for promoting communication between case managers and clients with schizophrenia. Ratings in 'Symptom record', 'Daily life record', and 'Scales' modules are stored in graphic or table form representing changes in them and shared with case managers. Conclusion : The interactive function of this application is the key characteristics that distinguishes it from other mobile self-treatment tools. This smartphone application may contribute to the development of a youth- and customer-friendly case management system for individuals with early psychosis.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.93-112
• /
• 2015

Depending on the change in consumer's consumption pattern, existing retail shop has evolved in hypermarket or convenience store offering grocery and daily products mostly. Therefore, it is important to maintain the inventory levels and proper product configuration for effectively utilize the limited space in the retail store and increasing sales. Accordingly, this study proposed proper product configuration and inventory level strategy based on RFM(Recency, Frequency, Monetary) model and SOM(self-organizing map) for manage the retail shop effectively. RFM model is analytic model to analyze customer behaviors based on the past customer's buying activities. And it can differentiates important customers from large data by three variables. R represents recency, which refers to the last purchase of commodities. The latest consuming customer has bigger R. F represents frequency, which refers to the number of transactions in a particular period and M represents monetary, which refers to consumption money amount in a particular period. Thus, RFM method has been known to be a very effective model for customer segmentation. In this study, using a normalized value of the RFM variables, SOM cluster analysis was performed. SOM is regarded as one of the most distinguished artificial neural network models in the unsupervised learning tool space. It is a popular tool for clustering and visualization of high dimensional data in such a way that similar items are grouped spatially close to one another. In particular, it has been successfully applied in various technical fields for finding patterns. In our research, the procedure tries to find sales patterns by analyzing product sales records with Recency, Frequency and Monetary values. And to suggest a business strategy, we conduct the decision tree based on SOM results. To validate the proposed procedure in this study, we adopted the M-mart data collected between 2014.01.01~2014.12.31. Each product get the value of R, F, M, and they are clustered by 9 using SOM. And we also performed three tests using the weekday data, weekend data, whole data in order to analyze the sales pattern change. In order to propose the strategy of each cluster, we examine the criteria of product clustering. The clusters through the SOM can be explained by the characteristics of these clusters of decision trees. As a result, we can suggest the inventory management strategy of each 9 clusters through the suggested procedures of the study. The highest of all three value(R, F, M) cluster's products need to have high level of the inventory as well as to be disposed in a place where it can be increasing customer's path. In contrast, the lowest of all three value(R, F, M) cluster's products need to have low level of inventory as well as to be disposed in a place where visibility is low. The highest R value cluster's products is usually new releases products, and need to be placed on the front of the store. And, manager should decrease inventory levels gradually in the highest F value cluster's products purchased in the past. Because, we assume that cluster has lower R value and the M value than the average value of good. And it can be deduced that product are sold poorly in recent days and total sales also will be lower than the frequency. The procedure presented in this study is expected to contribute to raising the profitability of the retail store. The paper is organized as follows. The second chapter briefly reviews the literature related to this study. The third chapter suggests procedures for research proposals, and the fourth chapter applied suggested procedure using the actual product sales data. Finally, the fifth chapter described the conclusion of the study and further research.

• Journal of Distribution Science
• /
• v.11 no.6
• /
• pp.41-50
• /
• 2013

Purpose - Inducing consumers' behavioral intent to use an outlet shopping center is a critical issue for managers since it can be used as a guide for developing marketing strategies. Low prices could lead to a growth in retail purchases, but there might also be a positive relationship between prices and customer perceptions of product quality. The extent to which consumers use price as a predictor of quality may differ according to the availability of important alternative cues such as brand, store name, and identity salience triggered by the store. Consumers can obtain non-economic benefits from marketing exchanges that go beyond basic economic achievement. We argue that identity salience can play a crucial mediating role when consumers, acting as exchange partners, seek to obtain social benefits. This study shows that identity salience could mediate the relationship between identity salience-inducing factors such as multi-finality, prestige and role performance, and consumers' behavioral intent to use an outlet shopping center. Research design, data and methodology - The survey was conducted on college students enrolled in marketing classes. A total of 200 questionnaires were distributed, of which only 194 were returned. After five incomplete questionnaires were excluded, a final sample of 189 was used for empirical analysis. Using a covariance structural analysis in Amos17, we confirmed the fit of the research model and estimated its parameters by using the maximum likelihood method. Results - The results of the hypotheses testing are as follows. First, both identity salience and economic benefits have positive effects on the behavioral intent to use an outlet shopping center. Second, role performance, prestige, and multi-finality have positive effects on identity salience. Finally, the additive analysis of the direct effects of identity salience-inducing factors shows that the role performance, prestige, and multi-finality factors have no direct effects on the behavioral intent to use an outlet shopping center, suggesting that identity salience plays a positive mediating role. Conclusions - This study informs marketers that not only price but shoppers' identity salience directly affects their intent to visit an outlet shopping center. To strengthen shoppers' identity salience, marketers should find ways to help shoppers fulfill their multiple social roles, realize their multiple goals, and achieve prestige. In other words, outlet shopping centers must improve their personal service environment in order to enhance their employees' service quality and assist the execution of multi-finality by minimizing the perceived costs (e.g., travel time, effort) associated with shopping trips, thus making it easier for consumers to combine visits to multiple stores in outlet shopping centers and buy the items required for their consumption goals. Outlet shopping centers must also offer assortments with both breadth and depth in order to help consumers play the social roles their social networks have given them.

• Journal of Trauma and Injury
• /
• v.22 no.1
• /
• pp.51-56
• /
• 2009

Purpose: The purpose of this study was to investigate environmental factors contributing to childhood home slip-down injuries. Methods: Among a total of 2,812 injured children in our Customer Injury Surveillance System (CISS), we performed a prospective study on 262 children with home slip-down injuries who visited the pediatric emergency department of Asan Medical Center between March 2008 and February 2009. We made a frequency analysis on parameters such as activities just before the accident, the presence of any obstacles or lubricant materials, specific home place in the home where the injuries occurred, flooring materials on which the slip-down happened, additional objects hit after slip down, the site and kind of injury, the duration of therapy, and the disposition. Results: Walking was the most common activity just before the injury. Because rooms and bathrooms were most common places in the home for slip down injuries, laminated papers/ vinyl floor coverings and tiles were the most common flooring materials used in the places where the injuries occured. Most commonly, no obstacles caused the children to slip down, but the furniture, stairs, doorsills, wetness, or soapy fluid followed after that. Over half of the children who slipped (58%) also collided with other than the floor itself after the slip-down, most common objects hit were the edges of the furniture, and doorsills, followed by stairways. The head and neck were the most commonly injured sites, and a laceration was the most common kind of injury. Most children needed less than 1 week of therapy, only 4 children (1.53%) admitted. There were no mortalities. Conclusion: The environmental factors contributing to slip-down injuries were the bathroom, laminated papers/vinyl floors, the furniture, stairs, doorsills, and wetness or soapy fluid. Especially, the furniture, stairs, and doorsills can be both primary obstacles and secondary collision objects. For the safety of our children, we must consider these factors on housing, when decorating or remodeling our house.

• 한국노년학
• /
• v.30 no.4
• /
• pp.1163-1177
• /
• 2010

This study was conducted to establish the appropriate facilities criteria of the Korean welfare devices center. We e-mail surveyed 194 welfare devices centers and analysed 13 blueprints of them. We established the following proper principles of facilities. First, consist type and area of room should depend on the type of welfare devices centers. Second, The flow of human and welfare devices should be simple. Third, the area calculated on the base of intent of center owner and the size of beds, wheelchairs, etc. Fourth, exhibit room facing with roadside may obtain advertising effect. Fifth, the storage and disinfecting room should use different entrance, and avoid the intersection of flow to prevent cross-contamination. Sixth, the access road to the exhibition and consulting room should be able to approach by the wheelchair. seventh, office room should be invisible to keep customer's privacy. Direct Cleaning-disinfecting type center on the premise that the maximum 165m², middle 150m², intermediate 140m², display at least Consultation, Cleaning-disinfecting room, storage (clean, contaminated), the office, equipped with a parking space. Entrust Cleaning-disinfecting type center on the premise that a maximum 134m², middle 119m², intermediate 109m² exhibited minimal activity room, consultation room, office, equipped with a parking space, collecting welfare when importing equipment warehouse (clean, pollution) have been proposed to equip up to.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.12
• /
• pp.8800-8811
• /
• 2015

When the crucial role of the agent in communicating with the customer is acknowledged well enough to relieve the agent's stress, it will lead to the decrease of the agent's emotional labor and the improvement of the business organization's performance simultaneously. However, the research on the relationship between information system and the emotional labor has been scarcely conducted even though the importance of the emotional labor is actively researched and discussed these days. Therefore, much effort has been put in this study to fine out how the quality of airline call center information system affects expectations-conformation and how expectations-conformation and self-efficacy affect performance of Emotional Labors. Analysis of the results to target a call center agent 436 people, When you provide them with quality information systems, it increased satisfaction and pride in their job. This mechanisms subsequently reduces the strength of the emotion labor, which ultimately improves the service performance. The implications of this study can be summarized as following: First, this research presented practical guidelines to the organization's decision-makers related to the airline call center operations in order to introduce and expand successful call center information system. Second, this research suggested the possible method to inspect and diagnose the system by way of applying the measurement model mentioned in this research into the airline information system and analyzing it. Third, the performance-measuring model developed in order to measure the performance of the airline call center information system can also be used when we carry out the performance-measuring task in the similar information system as the basis of diagnosing the situation and presenting the driving directions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.466-475
• /
• 2020

Current performance evaluation of call center employees is dependent on the number of calls they have resolved, regardless of the individual and social characteristics of employees. However, since call center tasks are highly customer-oriented and emotional laborious, individual capability as well as social characteristics of employees is critical to performance. Therefore, this study analyzed the relationship between employees' individual/social characteristics and their performance. To extract individual characteristics, a repertory grid technique was employed, whereas social network analysis was conducted to extract the social characteristics of employees. Using individual and social characteristics as input variables, multiple regression was conducted to analyze the effect of each variable on performance. As a result, in-degree centrality of dining network, initiative characteristics, open characteristics, and enjoyment of studying were determined to be important variables for performance. This study is expected to be used in both performance management and human resource management of call center practices.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.12 no.1
• /
• pp.57-61
• /
• 2008

Purpose: $^{18}F$-FDG PET is to evaluate the tumor using glucose metabolism. Blood Glucose Level (BGL) is important factor that affects on a result of examination. But it often appears the distort result on diabetic patient due to a failure of BGL control. The aim of this study is to make a effective guideline for diabetic patient prescribed $^{18}F$-FDG PET and improve accuracy and reliability of examination. Materials and methods: A subject of study is 69 diabetic patients and divided them into 3 groups; 1) BGL is less than 120 mg/dl & performed PET, 2) BGL is over than 120 mg/dl & performed PET, 3) BGL is over than 120 mg/dl & not performed PET. And we investigated the type of diabetic medications and the time of dosage, whether they have meal or not. And we analyzed SUV of liver and mediastinum to recognize the effect of BGL on PET images. Results: As a methods to diabetic control, Amalyl showed high percentage of 27.5% in oral medication and Humulin R showed 14.5% in insulin. Their peak time was 2-3 hrs, 2-4 hrs and duration time was 24 hrs, 5-7 hrs. The number of that had a breakfast was 16, 7 mens (43.8%) couldn't perform PET as over 120 mg/dl and 5 mens (31.3%) performed PET as less than 120 mg/dl after they took a medication. When we set the SUV of normal for 1.5-2.0, 1.0-1.5 on liver and mediastinum, the percentage out of the range was 31.8%, 52.9%, 62.5% in 120-139 mg/dl, 140-159 mg/dl, 160-200 mg/dl respectively. Conclusions: We completed standardized guideline for diabetic patients. As a result of this study, improved customer satisfaction and increased economic benefits. It is expect to be a effective model in other PET centers.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.36 no.3
• /
• pp.227-231
• /
• 2010

Among various make-up products, foundations are widely used to express clear and flawless skin. Foundations can be classified by its formula to 3 types, liquid foundation, powder foundation, and oil dispersion foundation. Powder foundations are easy to carry and use, so it is commonly possessed. In the R&D point of view, the developing method of powder foundations can be classified again to 3 types. Dry-process, baked-process, and the wet slurry-process. The fact that the wet slurry-process goes through either the back injection method or the front injection method is previously known. The front injection process is used as the main method in this study. We observed the quality dependence on the kind of solvent and the powder coating system. In brief, when water was used as the main solvent, the hardness increased than when volatile silicones or hydrocarbons were used. And the sensory results were shown to prefer volatile solvents (silicones or hydrocarbons) over water. Similarly, when the amino acid-coating system was applied, the hardness was shown to increase, when silicone-coating system shown no specific change. By these results, tailor-made powder foundations targeting specific customer grades can be easily produced.