• Knowledge Management Research
• /
• v.23 no.2
• /
• pp.277-299
• /
• 2022

The massive card transaction data generated in the tourism industry has become an important resource that implies tourist consumption behaviors and patterns. Based on the transaction data, developing a smart service system becomes one of major goals in both tourism businesses and knowledge management system developer communities. However, the lack of rating scores, which is the basis of traditional recommendation techniques, makes it hard for system designers to evaluate a learning process. In addition, other auxiliary factors such as temporal, spatial, and demographic information are needed to increase the performance of a recommendation system; but, gathering those are not easy in the card transaction context. In this paper, we introduce CTDDTR, a novel approach using card transaction data to recommend tourism services. It consists of two main components: i) Temporal preference Embedding (TE) represents tourist groups and services into vectors through Doc2Vec. And ii) Deep tourism Recommendation (DR) integrates the vectors and the auxiliary factors from a tourism RDF (resource description framework) through MLP (multi-layer perceptron) to provide services to tourist groups. In addition, we adopt RFM analysis from the field of knowledge management to generate explicit feedback (i.e., rating scores) used in the DR part. To evaluate CTDDTR, the card transactions data that happened over eight years on Jeju island is used. Experimental results demonstrate that the proposed method is more positive in effectiveness and efficacies.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.419-437
• /
• 2023

As the number of thin filers in Korea surpasses 12 million, there is a growing interest in enhancing the accuracy of assessing their credit default risk to generate additional revenue. Specifically, researchers are actively pursuing the development of default prediction models using machine learning and deep learning algorithms, in contrast to traditional statistical default prediction methods, which struggle to capture nonlinearity. Among these efforts, Graph Neural Network (GNN) architecture is noteworthy for predicting default in situations with limited data on thin filers. This is due to their ability to incorporate network information between borrowers alongside conventional credit-related data. However, prior research employing graph neural networks has faced limitations in effectively handling diverse categorical variables present in credit information. In this study, we introduce the Transformer embedded Graph Convolutional Network (TeGCN), which aims to address these limitations and enable effective default prediction for thin filers. TeGCN combines the TabTransformer, capable of extracting contextual information from categorical variables, with the Graph Convolutional Network, which captures network information between borrowers. Our TeGCN model surpasses the baseline model's performance across both the general borrower dataset and the thin filer dataset. Specially, our model performs outstanding results in thin filer default prediction. This study achieves high default prediction accuracy by a model structure tailored to characteristics of credit information containing numerous categorical variables, especially in the context of thin filers with limited data. Our study can contribute to resolving the financial exclusion issues faced by thin filers and facilitate additional revenue within the financial industry.

• Asia Marketing Journal
• /
• v.16 no.4
• /
• pp.75-87
• /
• 2015

As more companies become interested in global markets, it has become crucial for firms to create globalized brands whose positioning, advertising strategy, personality, looks, and feel are consistent across nations. The purpose of this study is to investigate the global branding strategy of the Hyundai Motor Company (hereafter HMC) in order to show how the company processes its branding strategy. HMC, one of the leading global companies in the automobile industry, set up its brand identity as "Modern premium", in alignment with their new slogan "New Thinking New Possibilities", in 2011. The aim of the "Modern premium" concept was to provide consumers with new experiences and values beyond their expectations. HMC wanted their consumers to think of their cars as not only a medium of transportation but as a life space, where they can share experiences alongside HMC. In an effort to conduct consumer research in 5 different nations, HMC selected "brilliant" as a key communication concept. The word "brilliant" expresses the functional, experiential, and emotional dimensions of HMC. HMC furthermore chose "live brilliant" as a key campaign message in order to reinforce their communication concept. After this decision, the "live brilliant" campaign was exhibited through major broadcast channels around the world. The campaign was the company's first worldwide brand campaign, where a single message was applied to all major markets, with the goal of building up a consistent image as a global brand. This global branding strategy is worth examining due to its significant contribution to growth generation in the global market. Overall, the 'live brilliant' global brand campaign not only improved HMC's reputation image-wise, with the 'Modern Premium' conceptualization of the brand as 'simple', 'creative' and 'caring', but also improved the consumer's familiarity, preference and purchase intention of HMC. In fact, the "live brilliant" campaign was a successful campaign which increased HMC's brand value. Notably, HMC's brand value increased continuously and reached 9 billion US dollars in 2013, leading it to reach 43rd place in the Global Brand Rankings according to the brand consulting group Interbrand. Its brand value largely surpassed that of Nissan (65th) and Chevrolet (89th) in 2013. While it is true that the global branding strategy of HMC involved higher risks, it was highly successful according to cross-nation consumer research. Therefore, this paper concludes that the global branding strategy of HMC made a positive impact on its performance. We further suggest HMC to combine its successful marketing with social media such as Facebook, Twitter, and Instagram and embrace digital media by extending its brand communication horizon to the mobile internet

• Clean Technology
• /
• v.15 no.2
• /
• pp.81-90
• /
• 2009

In this study various cleaning evaluation methods were tested and comparatively evaluated to help cleaning industry. In order to select alternative cleaning agents objectively and systematically, various cleaning evaluation methods such as gravimetric, optically simulated electron emission (OSEE), contact angle, and analytical instrument methods were employed for cleaning contaminants such as flux, solder and grease. The analytical instruments used in this work were Fourier transform infrared spectroscopy (FTIR), ultraviolet visible spectroscopy (UV-VIS) and high performance liquid chromatography (HPLC). The gravimetric method was able to measure cleaning efficiencies easily and simply, but it was not easy to analyze them precisely because of its limitation in the gravimetric measurement. However, the OSEE technique was able to measure quickly and precisely the clean ability of cleaning agents in comparison with the gravimetric method. The contact angle method was found to be necessary for taking special precaution in its application to the cleaning evaluation due to possible formation of tiny organic film on the substrate surface which might be generated from contaminants and cleaning agents. In case of precision analysis that cannot be done by gravimetric method, fine analytical instruments such as UV-VIS, FTIR and HPLC could be used in analyzing trace amount of flux, solder and grease quantitatively, which were extracted from the surface by special solvents.

• Clean Technology
• /
• v.16 no.2
• /
• pp.103-116
• /
• 2010

It has been reported that the LCD panel market in the FPD industry is become growing and its panel size and production capacity are increasing, and its manufacturing technique is improved every year. FPD manufacturing process requires high cleanliness in its overall process. Especially, FPD cleaning process which accounts for 30~40% of total manufacturing process is very important in its technological and productivity aspects. It is difficult to remove residual liquid-crystal in the fine gap after liquid-crystal injection process in the cell. In this study, aqueous cleaning agents with excellent cleaning, rinsing, and penetrating abilities, but minimum ion content for LCD panel were formulated through mixing glycol ether-type and glycol dimethyl ether-type solvents and nonionic surfactants which are widely used as raw materials for alternative cleaning agents because of environmental regulation at home and abroad. And the formulated cleaning agents were applied to clean FPD liquid crystal after its injection in the cell. Physical properties, cleaning efficiencies, and rinsabilities of the formulated cleaning agents with different combination ratios of solvents, surfactants and additives were measured. As experimental results, the formulated cleaning agents showed higher wetting indices and cloud point than the traditional commercial cleaning agent. And it was found that cleaning efficiencies of the formulated cleaning agents were influenced by the structure of main solvents in them and the types of liquid crystal as soil for cleaning. The best cleaning agents among the formulated cleaning agents showed similar cleaning efficiencies and better rinsabilities compared to the conventional cleaning agent.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.8
• /
• pp.145-152
• /
• 2009

Manufacturer's competitiveness in the MRO industry, which is to stimulate the growth of the business-to-business e-commerce market, has recently become more important. A nuclear parts manufacturer was supplying products based on irregular demand from clients which differs from ordinary MRO business practices. The reason for this is the Nuclear Parts Manufacturer has fallen behind the e-commerce performance of other industries, and they lack global competitiveness due to the low efficiency of the individual companies within it. In this study, we developed an MRO based a-Marketplace system to minimize repetitive ordering of raw materials, lack of reusability and inefficiency of transaction processing which was a result of the former legacy business practice, In order to accomplish the purpose of this study, we implemented a web based automated CR system which considered the characteristics of the nuclear parts manufacturing: the system has sub modules such as ordering, product management, transaction management, warehousing and raw material handling. As a consequence of the system implementation, H corporate successfully automated ordering of raw materials, quotation processing and inventory management compared to the legacy business process, achieving increased efficiency by reducing wasteful resources.

• Journal of the Korean Regional Science Association
• /
• v.39 no.2
• /
• pp.3-18
• /
• 2023

The aim of this study is to analyze problems with regional development projects by examining their actual conditions and to propose measures to promote such projects based on the size of local cities. To achieve this goal, problems associated with regional development projects were analyzed, and measures for their promotion were derived by dividing these projects into planning, strategy, policy, and institutional sectors according to the size of local cities. The problems identified with regional development projects include diversification leading to similar and overlapping projects, lack of participation by local experts, top-down government structure for designating and supporting regional development projects, and insufficient budget. In order to address these issues, local experts have suggested differential measures based on the size of local cities. Specifically, in the planning sector, it was proposed that economic, cultural, social, and welfare functions be expanded and reorganized primarily around small and medium-sized cities, and that long-term strategies be established for regional large cities through various partnerships and step-by-step procedures. In the policy sector, it was suggested that the implementation of bottom-up development under the leadership of local governments should be focused on small and medium-sized cities, and that the transition from a specific industry-oriented policy to a corporate growth policy needs to be established around large cities. Finally, in the institutional sector, it was recommended that a performance evaluation system for the use of financial resources and a system for expanding financial resources should be established primarily in small and medium-sized cities.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.6 no.5
• /
• pp.367-377
• /
• 2016

The purpose of the projects for strengthening the Service Business Competitiveness, which had been sponsored by the Ministry of Trade, Industry and Energy, and managed by the NIPA, is to support for combining the whole business process of the SMEs with the business model considering the scientific aspects of the services, to enhance the productivity of them and to add the values of their activities. 5 organizations are selected in 2014, and 4 in 2015 as leading organizations for these projects. This study analyzed the efficiency of these projects using DEA. Throughout the analysis of the prior researches, this study used the amount of government-sponsored money as the input variable, and the number of new customer business, the sales revenue, and the number of new employment as the output variables. And the result of this analysis showed that the decision making unit 12, 15, and 21 was efficient. And from this study, we found out two more performance indicators such as, the number of new employment and the amount of sales revenue, besides the number of new customer businesses.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.4
• /
• pp.593-601
• /
• 2017

In this paper, we constructed the model of production/investment, distribution, and screening by using variables that can be considered at each stage according to the value chain stage of the movie industry. To increase the predictive power of the model, a regression analysis was used to derive meaningful variables. Based on the given variables, we compared the difference in predictive power between the artificial neural network, which is a machine learning analysis method, and the decision tree analysis method. As a result, the accuracy of artificial neural network was higher than that of decision trees when all variables were added in production/ investment model and distribution model. However, decision trees were more accurate when selected variables were applied according to regression analysis results. In the screening model, the accuracy of the artificial neural network was higher than the accuracy of the decision tree regardless of whether the regression analysis result was reflected or not. This paper has an implication which we tried to improve the performance of movie prediction model by using machine learning analysis. In addition, we tried to overcome a limitation of linear approach by reflecting the results of regression analysis to ANN and decision tree model.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.71-84
• /
• 2021

Since small and medium-sized enterprises fell short of the securement of technological competitiveness in the field of big data and artificial intelligence (AI) field-core technologies of the Fourth Industrial Revolution, it is important to strengthen the competitiveness of the overall industry through technology commercialization. In this study, we aimed to propose a priority related to technology transfer and commercialization for practical use of public research results. We utilized public research performance information, improving missing values of 6T classification by deep learning model with an ensemble method. Then, we conducted topic modeling to derive the converging fields of big data and AI. We classified the technology fields into four different segments in the technology portfolio based on technology activity and technology efficiency, estimating the potential of technology commercialization for those fields. We proposed a priority of technology commercialization for 10 detailed technology fields that require long-term investment. Through systematic analysis, active utilization of technology, and efficient technology transfer and commercialization can be promoted.