• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.26-32
• /
• 2020

There are many airline customer evaluation data, but they are insufficient in terms of predicting customer satisfaction in practice. In particular, they are generally insufficient in case of verification of data value and development of a customer satisfaction prediction model based on customer evaluation data. In this paper, airline customer satisfaction analysis is conducted through an experiment of correlation analysis between customer evaluation data provided by Google's Kaggle. The difference in accuracy varied according to the three types, which are the overall variables, the top 4 and top 8 variables with the highest correlation. To build an airline customer satisfaction prediction model, they are applied to three classification algorithms of Random Forest, SVM, DNN and conduct a classification experiment. They are divided into training data and verification data by 7:3. As a result, the DNN model showed the lowest accuracy at 86.4%, while the SVM model at 89% and the Random Forest model at 95.7% showed the highest accuracy and performance.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.38 no.1
• /
• pp.69-87
• /
• 2013

Recently a large number of people have been using social networking and microblogging services such as Facebook and Twitter. These mediums play a pivotal communication channel in a business-to-customer (B2C) relationship. Given its importance in today's business, companies have invested in the strategic application of social network services to reach out to customers. This study provides a blueprint for mechanisms for successful execution of social network services in the context of developing an effective B2C relationship, such as customer participation behavior. The S-O-R(Stimulus-Organism-Response) framework lays out the foundation for developing our research model and provides a structured view for understanding customer participation behavior on brand loyalty. For the methodology, this study employed a mixed-method approach. Additionally, in order to provide empirical evidences, a total of 121 respondents have completed the survey. All the data were compiled and analyzed through structural equation modeling and were implemented in partial least square (PLS). To sum up, this study presented theoretical and practical implications by providing the effect of customer participation behavior on brand loyalty through B2C microblogging.

• Journal of Information Technology Applications and Management
• /
• v.22 no.2
• /
• pp.123-148
• /
• 2015

Today the mobile devices including smart phones have influenced on the users' daily activities in the mobile internet society, and the expansion of social media has also affected on the purchasing behavior of consumers. This study examines whether the quality of corporate twitter, a typical social network service for call centers influences on the customer satisfaction, and brand loyalty. In order to achieve the research goal, the quality of twitter has been divided into four variables; information quality, service quality, system quality, and social quality. The results of our empirical analysis show that the three variables except service quality have significantly influenced on the customer satisfaction and the customer satisfaction also significantly has a casual effect on the brand loyalty. The empirical results are expected as a guideline to contribute on the practical improvement of customer service, satisfaction, and brand loyalty through corporate social network services such as corporate twitters in the future.

• Journal of Distribution Research
• /
• v.11 no.3
• /
• pp.55-78
• /
• 2006

In business-to-business setting, dyadic relationships between firms are of paramount interest. Recent developments in business practice strongly suggest that to understand these business relationships, greater attention must be directed to the embedded context within which dyadic business relationships take place. As a result, it is important to develop an understanding which is to move from dyadic business relationship to business networks. The purpose of the current study is (1) to identify types of network benefits: information acquisition, access to tangible resources, cooperative support from network members, (2) to model network benefit efforts on a customer orientation for customer firm, (3) to examine the relationship between network characteristics and network benefits. Adopting resource-based view and social capital theory, the conceptual model is proposed. In order to develop and test a model, this paper was empirically to examine how network characteristics can reinforce network benefits leading to focal firm's customer orientation using 123 firms. Through structural equation modeling, this research found that (1) density influences information acquisition, access to tangible resources, cooperative support from network members, (2) centrality increases information acquisition, access to tangible resources. We also find that information acquisition, access to tangible resources, cooperative support from network members enhances focal firm's customer orientation. Finally, We discuss several theoretical and practical implications, and suggest limitations for the research and future research issue.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.10
• /
• pp.1733-1750
• /
• 2011

In the early stages of a software project, it is critical to understand the needs of the customers and elicit their customer requirements. Various requirements elicitation methods have been proposed. However, existing methods still have the limitations such as a limited number of target customers, limited expression of customers' opinions, and difficulty in collecting the customers' opinions continuously. A novel method for eliciting customer requirements is proposed by utilizing a social network service (SNS), which is a shared source of raw information of the customers' needs and opinions. The proposed method is validated to show its effectiveness in overcoming the limitations of existing methods.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.33-36
• /
• 2020

Virtual try on is getting interested from researchers these days because its application in online shopping. But single pose virtual try on is not enough, customer may want to see themselves in different pose. Multiple pose virtual try on is getting input as customer image, an in-shop cloth and a target pose, it will try to generate realistic customer wearing the in-shop cloth with the target pose. We first generate the target segmentation layout using conditional generative network (cGAN), and then the in-shop cloth are warped to fit the customer body in target pose. Finally, all the result will be combine using a Resnet-like network. We experiment and show that our method outperforms stage of the art.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.10a
• /
• pp.189-206
• /
• 2005

Much of work on network externality assumed network effects are dependent on the network size. Therefore, very little consideration is given to the view that marginal benefits from joining the network may not increase with the network size if consumer benefits come from the direct interaction with neighbors, namely local network. In this study, we used the agent-based simulation method to reexamine the effectiveness of the traditional network market strategy under the presence of the local network where two incompatible technologies compete. We found that the strategy of growing an initial customer base is not effective under the presence of the local network. Our study also showed that targeting customers based on their technology Preference is not as effective as targeting customers within the same local network. As a result, the focus of a network market strategy should be directed to taking advantage of the customer network.

• Journal of Information Management
• /
• v.42 no.2
• /
• pp.211-234
• /
• 2011

The development of information technology improves the globalization of the world economy. This change was able to expand the cyber space, and the online community known as the cyber community is made within the existing offline community. From the cyber community's activity, the concept of social network services created, and recently developed social computing. Social computing is the current situation and the next step in the online community. Currently, most CIOs are using social computing for workplace empowerment. As online transactions become more active, the strategy to increase customer loyalty in Internet shopping is an effective tool to increase profit for the company, and as a method to maintain competitive. With the growth of electronic commerce, through insurance of customer loyalty on the Internet, a company can establish a long-term relationship with customers, so for this, it is important to have reliable relationship with customers. Also, through advertisement and commercial information, the cognition of Internet shopping looks can be effective in retaining customers. In this study, it explores how social computing and trust and cognition of Internet shopping are effective in maintaining customer loyalty. As the result of study, the trust and cognition of Internet shopping are significantly effective on customer loyalty, but the sense of social computing. Still, social computing has not matured enough to be as effective in retaining customer loyalty. However, it does indicate that social computing has significantly increased the trust and cognition in Internet shopping. In this study, as the concepts of the social network service and social computing are applied in Internet shopping, which are actively discussed by scholars, it is expected that the basis of the study could improve and present the idea of social shopping.

• 한국정보통신설비학회:학술대회논문집
• /
• 2005.08a
• /
• pp.222-225
• /
• 2005

• ETRI Journal
• /
• v.30 no.2
• /
• pp.282-289
• /
• 2008

We propose a new mini-slot transmission scheme for a passive optical network (PON) in which each customer can be switched either to access mode or to internetworking mode dynamically. In this paper, we present the system implementation (called LAN-PON) as well as the performance of the proposed transmission scheme to illustrate its feasibility and benefits. A mini-slot scheme can rapidly reduce the queuing delay, which increases due to the flooding of the deflected packets in a deflection scheme. We evaluate the impact of mode switching time on the bandwidth gain (throughput) and delay of local area network (LAN) traffic in the LAN-PON with a mini-slot scheme. We also analyze a theoretical delay model of the proposed scheme. The simulation results demonstrate that switching time has an impact on LAN performance, and the average packet delay of the proposed scheme is significantly improved compared to that of the deflection scheme.