• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.47 no.1
• /
• pp.57-75
• /
• 2019

Soundscapes have the potential to help people experience the historical background and cultural traditions by the scenery of a local area and to be used as a cultural and tourism resource. This concept was first explained in detail by M. Schafer and has been developed as a new way of experiencing landscapes using various senses. This research studied the soundscape of Kyodong Island, the so-called "Island of Peace" and designed new cultural acoustic content for education and tourism. Kyodong Island is located right below the Northern Limit Line and the whole island is in the Civilian Controlled Area. The political and economic status of the island has been changed dynamically by the Korean War and the division of the country. These days, the island needs to realize the vision of the "Island of Peace" in a more creative way using local resources, including its "cold war landscape" and the natural scenery of the region. This research applied the concept of a soundscape to document the island, and to reproduce it in an artistic way. A workshop was conducted to learn concepts and techniques of soundscapes with a sound artist. Listening, recording, conducting interviews, and literature research was used to study the soundscape of the island. After that, this research reconstructed the soundscape of the island through a soundscape composition. The main theme of the composition story was the "Hope and Wish for the Harmony and Peace" to show the vision of the "Island of Peace". The initial sub-theme for the introduction part was "First Encounter with Kyodong Island" arranging the representative soundscape, which could be the first impression of the region. The second sub-theme was "War and Tension" using several soundscapes as a metaphor for the tragedy of the Korean War. The third sub-theme was "Everyday Life of Kyodong Island" which described the energy of the present day, after the wounds of the war have healed. The final sub-theme was "Harmony and Peace" using traditional music and keynote sounds of the region as a reminder of the peaceful past, before the war. The recording files were documented as two types of sound maps. One was a two-dimensional map to show the soundscapes from one point of view, and the other used the online application called "Sound Around You". The final artwork was displayed at an exhibition and uploaded on YouTube to be shared publicly. Through this project, we discovered the potential of soundscapes as a medium to preserve the history and local identity, as well as presenting a new vision. The artwork will be exhibited at historically and culturally meaningful places on the Island to utilize the underused places as local tourist attractions and educational resources.

• Korea Trade Review
• /
• v.41 no.4
• /
• pp.185-219
• /
• 2016

The Chinese cosmetics market is rapidly expanding, but various problems have also emerged, including exaggerated advertisement, lack of accurate information on product usage and the emergence of imitation products. For this reason, cosmetics companies have been making efforts to convince Chinese consumers of their brand authenticity and trust. In particular, Korean cosmetics firms have been using Hallyu stars who are largely popular among Chinese consumers as a means to raise their brand authenticity and trust. The aim of this study was to view Hallyu stars as human brands in the Chinese cosmetics market and verify whether the Chinese consumers' attachment toward Korean celebrities help the consumers perceive the authenticity of the brands advertised by the stars, and whether such brand authenticity affects the Chinese consumers' trust in Korean cosmetics brands. Furthermore, based on the fact that brand authenticity is defined and classified differently according to the type of product, this study observed the authenticity of Korean cosmetics brands from the aspect of product, employee and company based on previous research conducted on cosmetics brand authenticity. To this end, this study surveyed Chinese consumers for a month by using a representative survey website (http://www.sojump.com) that actively shares information related to cosmetics. A total of 394 surveys were used in the empirical analysis. The results of empirical analysis indicated that Chinese consumers' attachment toward Hallyu stars spreads to the Korean cosmetics brands advertised by the celebrities to have a positive effect on the brand authenticity perceived by Chinese consumers, including the authenticity of product, employee and company. Results also showed that the authenticity of Korean cosmetics brands, including product, employee and company, affected Chinese consumers' trust in the brands. The results of this study can provide implications regarding advertising or marketing strategies using Hallyu stars that can be utilized by Korean cosmetics companies to improve brand authenticity and reliability perceived by Chinese consumers in the Chinese cosmetics market, where brand authenticity and reliability are important.