• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.221-241
• /
• 2018

Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

• The Research Journal of the Costume Culture
• /
• v.20 no.6
• /
• pp.895-911
• /
• 2012

The purpose of this study was to examine consumers' perceptions of eco-friendly children's-wear and their impact on the selection criteria for children's-wear and stores. A descriptive survey method using a self-administered questionnaire was employed. The sample consisted of mothers with children under the age of 13 residing in Seoul and the Gyeonggi area. Data were collected from September 2011 to October, 2011. The collected data were analyzed to find the differences between purchasers and non-purchasers of eco-friendly children's-wear in terms of their perceptions of eco-friendly children's-wear, as well as the influence of these perceptions on the consideration degree of criteria for the selection of children's wear and store. The results indicate that perceptions of eco-friendly children's-wear implied five key factors related to quality reliability, expected value, style, degree of recognition, and dissatisfaction with design and price. The results also revealed some differences between the group purchasing eco-friendly children's-wear and the group not purchasing eco-friendly children's-wear. These different perceptions were related to the aspects of quality reliability, expected value, style, degree of recognition. In general, the non-purchasing group displayed a lower mean score than the purchasing group. Both groups showed a low interest in aesthetic appreciation and the degree of recognition factor. The results showed that consumer's perceptions of eco-friendly children's-wear had an influence on the criteria for the selection of children's-wear and store type in both groups. Considering the findings of the study, it is clear that both purchasers and non-purchasers of eco-friendly children's-wear showed differences in their perceptions and purchasing behavior. Therefore, marketing strategies to appeal to the non-purchasing group should be differentiated from strategies used to ensure the loyalty of the purchasing group.

• CRM연구
• /
• v.2 no.2
• /
• pp.71-88
• /
• 2009

The purpose of this thesis is to examine the effects of e-CRM activities by the internet shopping mall companies on the purchase activities of purchase customers and the potential customers. The internet shopping companies utilize e-CRM to systematically identify customers' varying demands, and to utilize the results as marketing tools, thus producing a significant effect on the potential customers by generating customer feedback through e-Community. Contrary to their intention, however, cognitive dissonance can occur through e-Community, which may lead to customers' complaints. If these complaints are not properly managed and settled in a timely manner, they can be transferred to other potential customers, and the conformity phenomenon could be created by other complaining customers. Findings obtained through this thesis are as follows: If cognitive disharmony is created by customers who purchased products through the internet shopping malls, this can lead to private complaining behaviors, and subsequently, these behaviors are formed through e-Community. If the internet shopping mall companies do not take any timely and proper measures to intervene in the stage of private complaining behaviors in the first place, these behaviors will immediately escalate into the public complaining behaviors. Furthermore, the complaints will be transferred to other potential customers, ultimately resulting in their swift expansion. In other words, contrary to intention of the internet shopping mall companies, e-CRM does not facilitate the potential customers purchase decision, it rather affects them to postpone or withdraw their purchase decision. Accordingly, the internet shopping mall companies are required to manage e-Community with extreme care, and they should promptly respond to the complaining customers so that e-Community can function properly.

• Journal of Korean Society for Quality Management
• /
• v.50 no.2
• /
• pp.287-304
• /
• 2022

Purpose: The size of the salad consumption market has expanded since Covid-19, and continuous growth is predicted. Therefore, by extracting influential core purchasers in the salad consumption market and analyzing their purchasing behaviors and consumer types, this study intended to provide basic data for establishing a marketing strategy. Methods: The analysis data is the purchasing data of 576 people who have purchased salads between 2016 and 2020 (panel data of the Rural Development Administration), and in the social network analysis, the centrality structure was analyzed. Results: First, in the results of analyzing the causes of the rapid increase in salad consumption in 2020, it was found that the increase in consumption of new purchasers (n=102) had little effect. The existing consumer type (n = 474), which has been the majority of the salad consumption market so far, were consumers with stable income. However, the results of study indicated that the type of consumers has expanded since low-income class as well as high-income class increased consumption of purchasing salad. Second, in the results of analyzing the types of key purchasers with great influence in the salad consumption market, there was a difference from the results of frequency analysis in age, number of family members, existence/absence of children, and income decile. This suggests that there should be a difference between the type of customers according to the apparent quantitative figure and the actual influential purchasers. Third, in the results of analyzing the salad purchasing behaviors of core purchasers, the purchasing site for existing purchasers was large-scale marts and for new purchasers it was corporate-type supermarkets. Purchases were concentrated on Saturdays for both existing and new purchasers. As for the purchased products, existing purchasers had a high preference for products made of chicken, and new purchasers had a high preference for vegetable/fruit salad. In particular, in the results of purchased products by age group, in the case of 50s and 60s, it was an interesting result that there was a difference between the products purchased by the existing and new purchasers even though they were the same age. Conclusion: When establishing a marketing strategy in the salad consumption market, it is necessary to pay attention to the purchasing behavior of key buyers.

• Asia Marketing Journal
• /
• v.15 no.3
• /
• pp.15-29
• /
• 2013

Shopping is considered a 'must-do' activity for most people on travel. One of the major parts of tourist shopping is the purchasing of souvenirs. Souvenirs are universally associated with tourism as a commercially produced and purchased object to remind the purchaser of the experience. Recently, Korea becomes one of the most popular destinations that many Asian tourists like to visit. Among those Asian tourists, the number of Thai tourists bound for Korea shows an incredible rapid growth. Thai people pick Korea and Seoul as their favorite country and city to visit for three consecutive years since 2009. One of the major reasons why Thais are choosing to tour Korea is the enthusiasm for Korean pop culture. That is, 'Hallyu' has influenced Thais' decision to visit Korea and purchase Korean products. The primary objective of the current research is to explore the shopping experiences of Thai tourists, specifically their souvenir shopping. It adopts a reflexive interpretive approach to bring light to the various meanings Thai tourists attach to the souvenirs they purchase in Korea. In order to accomplish the objective, the individual interviews were conducted. A total of 12 Thais who have experienced traveling in Korea participated in the study. Four themes were identified through interview text analysis. First, the research participants almost always purchase souvenirs in Korea because the souvenirs represent their identities as tourists. Especially, they purchase the souvenirs as gifts for others, including family members, friends, and colleagues. The souvenirs as gifts show love and thanks to others, and they cement the social relationship. However, purchasing souvenirs for others is more like the moral obligations which evoke the psychological stress. Secondly, the research participants feel closer to Korea while shopping souvenirs around. Thirdly, they obtain imaginative experiences and pleasure through souvenirs related to the Korean pop culture. Souvenirs provide them to visually extraordinary experiences. Lastly, souvenirs purchased in Korea act as visible status marker when they go back to Thailand. They show the socioeconomic status and lifestyles. Tourists themselves and others place special value to souvenirs that were purchased out of Thailand. The findings of this study are of both academic and practical importance. Souvenirs are among the most pervasive elements of the travel experience. However, souvenir shopping is the complicated consumer behavior within tourism both from business and social science perspectives. Along the same line, it needs strategic approaches in order to maximize the economy effects. It concludes by suggesting how further research could offer unique insights into how the souvenirs are positioned both in the context of tourism academics and industry.

• The Journal of Fisheries Business Administration
• /
• v.34 no.2
• /
• pp.75-90
• /
• 2003

When we think of fundamental problems of the aquaculture industry, there are several strict conditions, and consequently the aquaculture industry is forced to change. Fish aquaculture has a structural supply surplus in production, aggravation of fishing grounds, stagnant low price due to recent recession, and drastic change of distribution circumstances. It is requested for us to initiate discussion on such issue as “how fish aquaculture establishes its status in the coastal fishery\ulcorner, will fish aquaculture grow in the future\ulcorner, and if so “how it will be restructured\ulcorner” The above issues can be observed in the mariculture of yellow tail, sea scallop and eel. But there have not been studied concerning seabream even though the production is over 30% of the total production of fish aquaculture in resent and it occupied an important status in the fish aquaculture. The objectives of this study is to forecast the future movement of sea bream aquaculture. The first goal of the study is to contribute to managerial and economic studies on the aquaculture industry. The second goal is to identify the factors influencing the competition between production areas and to identify the mechanisms involved. This study will examine the competitive power in individual producing area, its behavior, and its compulsory factors based on case study. Producing areas will be categorized according to following parameters : distance to market and availability of transportation, natural environment, the time of formation of producing areas (leaderㆍfollower), major production items, scale of business and producing areas, degree of organization in production and sales. As a factor in shaping the production area of sea bream aquaculture, natural conditions especially the water temperature is very important. Sea bream shows more active feeding and faster growth in areas located where the water temperature does not go below 13∼14$^{\circ}C$ during the winter. Also fish aquaculture is constrained by the transporting distance. Aquacultured yellowtail is a mass-produced and a mass-distributed item. It is sold a unit of cage and transported by ship. On the other hand, sea bream is sold in small amount in markets and transported by truck; so, the transportation cost is higher than yellow tail. Aquacultured sea bream has different product characteristics due to transport distance. We need to study live fish and fresh fish markets separately. Live fish was the original product form of aquacultured sea bream. Transportation of live fish has more constraints than the transportation of fresh fish. Death rate and distance are highly correlated. In addition, loading capacity of live fish is less than fresh fish. In the case of a 10 ton truck, live fish can only be loaded up to 1.5 tons. But, fresh fish which can be placed in a box can be loaded up to 5 to 6 tons. Because of this characteristics, live fish requires closer location to consumption area than fresh fish. In the consumption markets, the size of fresh fish is mainly 0.8 to 2kg.Live fish usually goes through auction, and quality is graded. Main purchaser comes from many small-sized restaurants, so a relatively small farmer and distributer can sell it. Aquacultured sea bream has been transacted as a fresh fish in GMS ,since 1993 when the price plummeted. Economies of scale works in case of fresh fish. The characteristics of fresh fish is as follows : As a large scale demander, General Merchandise Stores are the main purchasers of sea bream and the size of the fish is around 1.3kg. It mainly goes through negotiation. Aquacultured sea bream has been established as a representative food in General Merchandise Stores. GMS require stable and mass supply, consistent size, and low price. And Distribution of fresh fish is undertook by the large scale distributers, which can satisfy requirements of GMS. The market share in Tokyo Central Wholesale Market shows Mie Pref. is dominating in live fish. And Ehime Pref. is dominating in fresh fish. Ehime Pref. showed remarkable growth in 1990s. At present, the dealings of live fish is decreasing. However, the dealings of fresh fish is increasing in Tokyo Central Wholesale Market. The price of live fish is decreasing more than one of fresh fish. Even though Ehime Pref. has an ideal natural environment for sea bream aquaculture, its entry into sea bream aquaculture was late, because it was located at a further distance to consumers than the competing producing areas. However, Ehime Pref. became the number one producing areas through the sales of fresh fish in the 1990s. The production volume is almost 3 times the production volume of Mie Pref. which is the number two production area. More conversion from yellow tail aquaculture to sea bream aquaculture is taking place in Ehime Pref., because Kagosima Pref. has a better natural environment for yellow tail aquaculture. Transportation is worse than Mie Pref., but this region as a far-flung producing area makes up by increasing the business scale. Ehime Pref. increases the market share for fresh fish by creating demand from GMS. Ehime Pref. has developed market strategies such as a quick return at a small profit, a stable and mass supply and standardization in size. Ehime Pref. increases the market power by the capital of a large scale commission agent. Secondly Mie Pref. is close to markets and composed of small scale farmers. Mie Pref. switched to sea bream aquaculture early, because of the price decrease in aquacultured yellou tail and natural environmental problems. Mie Pref. had not changed until 1993 when the price of the sea bream plummeted. Because it had better natural environment and transportation. Mie Pref. has a suitable water temperature range required for sea bream aquaculture. However, the price of live sea bream continued to decline due to excessive production and economic recession. As a consequence, small scale farmers are faced with a market price below the average production cost in 1993. In such kind of situation, the small-sized and inefficient manager in Mie Pref. was obliged to withdraw from sea bream aquaculture. Kumamoto Pref. is located further from market sites and has an unsuitable nature environmental condition required for sea bream aquaculture. Although Kumamoto Pref. is trying to convert to the puffer fish aquaculture which requires different rearing techniques, aquaculture technique for puffer fish is not established yet.