• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.19-42
• /
• 2012

Consumer consumption patterns are shifting rapidly as buyers migrate from offline markets to e-commerce routes, such as shopping channels on TV and internet shopping malls. In the offline markets consumers go shopping, see the shopping items, and choose from them. Recently consumers tend towards buying at shopping sites free from time and place. However, as e-commerce markets continue to expand, customers are complaining that it is becoming a bigger hassle to shop online. In the online shopping, shoppers have very limited information on the products. The delivered products can be different from what they have wanted. This case results to purchase cancellation. Because these things happen frequently, they are likely to refer to the consumer reviews and companies should be concerned about consumer's voice. E-commerce is a very important marketing tool for suppliers. It can recommend products to customers and connect them directly with suppliers with just a click of a button. The recommender system is being studied in various ways. Some of the more prominent ones include recommendation based on best-seller and demographics, contents filtering, and collaborative filtering. However, these systems all share two weaknesses : they cannot recommend products to consumers on a personal level, and they cannot recommend products to new consumers with no buying history. To fix these problems, we can use the information which has been collected from the questionnaires about their demographics and preference ratings. But, consumers feel these questionnaires are a burden and are unlikely to provide correct information. This study investigates combining collaborative filtering with the centrality of social network analysis. This centrality measure provides the information to infer the preference of new consumers from the shopping history of existing and previous ones. While the past researches had focused on the existing consumers with similar shopping patterns, this study tried to improve the accuracy of recommendation with all shopping information, which included not only similar shopping patterns but also dissimilar ones. Data used in this study, Movie Lens' data, was made by Group Lens research Project Team at University of Minnesota to recommend movies with a collaborative filtering technique. This data was built from the questionnaires of 943 respondents which gave the information on the preference ratings on 1,684 movies. Total data of 100,000 was organized by time, with initial data of 50,000 being existing customers and the latter 50,000 being new customers. The proposed recommender system consists of three systems : [+] group recommender system, [-] group recommender system, and integrated recommender system. [+] group recommender system looks at customers with similar buying patterns as 'neighbors', whereas [-] group recommender system looks at customers with opposite buying patterns as 'contraries'. Integrated recommender system uses both of the aforementioned recommender systems to recommend movies that both recommender systems pick. The study of three systems allows us to find the most suitable recommender system that will optimize accuracy and customer satisfaction. Our analysis showed that integrated recommender system is the best solution among the three systems studied, followed by [-] group recommended system and [+] group recommender system. This result conforms to the intuition that the accuracy of recommendation can be improved using all the relevant information. We provided contour maps and graphs to easily compare the accuracy of each recommender system. Although we saw improvement on accuracy with the integrated recommender system, we must remember that this research is based on static data with no live customers. In other words, consumers did not see the movies actually recommended from the system. Also, this recommendation system may not work well with products other than movies. Thus, it is important to note that recommendation systems need particular calibration for specific product/customer types.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.574-583
• /
• 2020

The aim of this study is to investigate the expenditure items and expenses for companion dogs and the appropriate considerations when choosing companion dog food for consumers who purchase dog food through the internet. The survey subjects consisted of 39 males (6.8%) and 532 females (93.2%), and it was found that most women purchase dog food through the internet. According to the age of dog owner, 184 (32.2%) were in their 20s and 241 (42.2%) in their 30s and 146 (25.6%) in their 40s or older. According to the age of the dogs, 200 (35%) were under 3 years old, 202 (35.4%) over 8 years old, and 169 (29.6%) were between 4 and 7 years old. The most preferred ingredient was chicken, regardless of dogs' owner or the dogs' age. Spending less than 100,000 won was most frequency reported, regardless of dog owner and the age of the dog, and major dog food was reported to be purchased in the order of online shopping malls and animal hospitals. In order to improve health function, it was determined that improvement of skin and hair is the most important, and next, was improvement of tooth bone formation and digestibility. When choosing food for companion dogs, nutritional composition of all the products was the most important consideration, followed by brand products with recognition, color, smell, shape, functional improvement products, and price of the products. Therefore, when developing a new product for companion dog food, consideration must be given not only to the nutritional components of all products, but also the brands, color, odor, shape, nutritional balance, functional improvement and price.

• Journal of Venture Innovation
• /
• v.3 no.1
• /
• pp.101-115
• /
• 2020

In the era of the 4th Industrial Revolution customers living began to come out, not inside the purchase funnel. Due to the diversity of product selection and the increase in digital channels, the way customers search for information and purchase it is changing innovatively. So, the customer journey in the digital age is much more complicated than the traditional funnel model suggests. Unlike many previous studies, this study was conducted for 1,200 customers in four product groups of fashion, automobile, cosmetics, and online shopping malls. As a result of the study, we investigated how digital self-efficacy plays a role in purchasing in a series of processes in which digital experience affects customer satisfaction and finally affects purchase. As a theoretical implication, as a result of introducing and testing digital self efficacy as moderated mediation effect. the digital self-efficacy between customer satisfaction and customer loyalty were determined to play a moderated mediation effect role. As a practical implication, it was necessary to actively utilize digital marketing for customers with high digital self-efficacy, but it was suggested that customers with low digital self-efficacy need to be careful about digital marketing fatigue.

• Journal of Distribution Science
• /
• v.13 no.6
• /
• pp.79-86
• /
• 2015

Purpose - The cosmetics industry is a traditional high value-added industry in terms of the domestic demand, small batch production systems, exclusive competition, and raw materials highly dependent on overseas countries as well as an oligopolistic market structure. However, new foreign brands and growing consumer awareness of inexpensive products, has triggered a shift. In line with changing lifestyles and the polarization of consumption, the industry faces a new market structure. Among its key characteristics is the cosmetics industry's numerous distribution channels (i.e., department stores, door-to-door sales, online shopping malls, brand shops, and discount stores). Therefore, the study of its distribution channels is essential. Research design, data, and methodology - The study analyzed channel distribution power divided into coercive and non-coercive power. The factors of coercive power included: unilateral request of an increase in commissions, interference in sales by taking advantage of a superior status, unilateral buck-passing at the time of a problem, unilateral request to stop sales activities, and a unilateral business contract; the factors of non-coercive power included favorable payment conditions, offers of various kinds of information, policy on commission reduction, pride in market entrance, and promotion support. In addition, the mediating variable "interdependence" was applied to the execution of department store (or mart) power and their shop conflicts and satisfaction to examine direct and indirect influential power. The methodology was a survey of managers of cosmetics shops in department stores (or marts). The questionnaire, based on a five-point Likert scale, included questions about basic personal information, execution of power, interdependence, conflict, and satisfaction. The study distributed 198 questionnaires and collected 131. Ten questionnaires with missing or hard to analyze data were excluded. Thus, 121 copies were analyzed. Results - According to the analysis, the execution of coercive power by department stores (or marts) did not affect interdependence, but the execution of non-coercive power did. Interdependence did not influence conflict, but did affect satisfaction. Additionally, the analysis revealed direct influential power: the execution of coercive power positively affected conflict and negatively influenced satisfaction; the execution of non-coercive power positively affected satisfaction. Conclusions - To offer suggestions for distribution business relations in the cosmetics industry, this study investigated how the execution of power by department stores (or marts) affected their shops. More specifically, it examined how much the execution of both coercive power and non-coercive power influenced conflict and satisfaction, and analyzed the mediating role of interdependence. In line with previous study results in various areas, coercive power was shown to be the source of conflict, leading to a decrease in satisfaction, whereas non-coercive power significantly positively influenced satisfaction. Moreover, non-coercive power increased interdependence, which led to greater satisfaction. As a result, interdependence had a mediating effect on non-coercive power and satisfaction. Based on the results, department stores (or marts) should look for improvements plans that increase interdependence. Such plans could alleviate conflict with the shops, increasing their satisfaction.

• Information Systems Review
• /
• v.18 no.2
• /
• pp.59-77
• /
• 2016

Although various recommendation techniques have been applied to the e-commerce market, few studies compare the intent to use these techniques from the customer's perspective. In this paper, we conduct a comparative analysis of customers' intention to use five recommendation techniques widely adapted by online shopping malls and focus on the differences in purchasing electronic goods and apparel products. The recommendation techniques are as follows: best-seller recommendation, merchandiser recommendation, content-based recommendation, collaborative filtering recommendation, and social recommendation. Additionally, we examine which factors influence customer intent to use the recommendation services. Data were collected through a survey administered to 220 e-commerce users with prior experience with recommendation services. Collected data were examined using analysis of variance and regression analysis. Results indicate statistically significant differences in customers' intention to use recommendation services according to the recommendation technique. In particular, the best-seller recommendation technique is preferred when purchasing electronic goods, whereas the content-based recommendation technique is preferred for apparel purchases. Factors such as personal characteristics and personality, purchasing tendency, as well as perception of the product or recommendation service affect a customer's intention to use a recommendation service. However, the influence of these factors varies depending on the recommendation technique. This study provides guidelines for companies to adopt appropriate recommendation techniques according to product categories and personal characteristics of customers.

• Journal of Information Technology Applications and Management
• /
• v.26 no.4
• /
• pp.51-69
• /
• 2019

One of the most considerate phenomena of the era of the Fourth Industrial Revolution is the use of digital devices. Digitalization is rapidly advancing through all areas of industry and life. Customer journey with digitalization is looking totally different from previous customer journey. The research targets were users of fashion, automobiles, cosmetics and online shopping malls. We analyzed 300 people for each valid questionnaire. The results of the study are as follows. First, it has been proven that digital experience affects positive (+) impact on purchasing intention and positive (+) impact on recommending intention and negative impact (-) on switching intent and subsequently affects positive impact (+) to purchase and incase of switching intent, negative impact (-) to purchase. Unlike traditional methods such as SPC(Service Profit Chain), the Digital experience to Purchase process Chain (DPC) has been identified to be suitable in the digital age. Second, the digital satisfied group (5 score-very satisfaction) has shown same result as above. However the digital neutral group (even though 4 score- satisfaction in five-point scale), specially in a highly competitive industry, has different from the satisfied group and 3 score-normal is same as dissatisfied group. It means that this group is that If there is a high level of attractiveness of substitute goods, there is a high possibility of switching them. It has supported Jones and Sasser [1995] that there have been two types of loyalty of true long-term loyalty and what we call false loyalty in the highly competitive industry zone which is commoditization or low differentiation, many substitutes, low cost of switching. Identifying true loyalty and false loyalty is crucial to establishing a customer experience strategy. it is necessary to actively utilize long-term digital experiences strategy to increase the total satisfaction of digital experience through all of customer purchasing journey in order to enhance the digital customer experience. It is difficult to see the effect as a one-time event. It should be scaled over the entire customer purchase process over a long period of time, which can positively affect purchase intention, recommendation intention, and conversion intention. This is also why it is difficult for second-runners to overtake first-runners in a short period.

• Journal of Intelligence and Information Systems
• /
• v.27 no.2
• /
• pp.1-15
• /
• 2021

If it is difficult for us to make decisions, we ask for advice from friends or people around us. When we decide to buy products online, we read anonymous reviews and buy them. With the advent of the Data-driven era, IT technology's development is spilling out many data from individuals to objects. Companies or individuals have accumulated, processed, and analyzed such a large amount of data that they can now make decisions or execute directly using data that used to depend on experts. Nowadays, the recommender system plays a vital role in determining the user's preferences to purchase goods and uses a recommender system to induce clicks on web services (Facebook, Amazon, Netflix, Youtube). For example, Youtube's recommender system, which is used by 1 billion people worldwide every month, includes videos that users like, "like" and videos they watched. Recommended system research is deeply linked to practical business. Therefore, many researchers are interested in building better solutions. Recommender systems use the information obtained from their users to generate recommendations because the development of the provided recommender systems requires information on items that are likely to be preferred by the user. We began to trust patterns and rules derived from data rather than empirical intuition through the recommender systems. The capacity and development of data have led machine learning to develop deep learning. However, such recommender systems are not all solutions. Proceeding with the recommender systems, there should be no scarcity in all data and a sufficient amount. Also, it requires detailed information about the individual. The recommender systems work correctly when these conditions operate. The recommender systems become a complex problem for both consumers and sellers when the interaction log is insufficient. Because the seller's perspective needs to make recommendations at a personal level to the consumer and receive appropriate recommendations with reliable data from the consumer's perspective. In this paper, to improve the accuracy problem for "appropriate recommendation" to consumers, the recommender systems are proposed in combination with context-based deep learning. This research is to combine user-based data to create hybrid Recommender Systems. The hybrid approach developed is not a collaborative type of Recommender Systems, but a collaborative extension that integrates user data with deep learning. Customer review data were used for the data set. Consumers buy products in online shopping malls and then evaluate product reviews. Rating reviews are based on reviews from buyers who have already purchased, giving users confidence before purchasing the product. However, the recommendation system mainly uses scores or ratings rather than reviews to suggest items purchased by many users. In fact, consumer reviews include product opinions and user sentiment that will be spent on evaluation. By incorporating these parts into the study, this paper aims to improve the recommendation system. This study is an algorithm used when individuals have difficulty in selecting an item. Consumer reviews and record patterns made it possible to rely on recommendations appropriately. The algorithm implements a recommendation system through collaborative filtering. This study's predictive accuracy is measured by Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Netflix is strategically using the referral system in its programs through competitions that reduce RMSE every year, making fair use of predictive accuracy. Research on hybrid recommender systems combining the NLP approach for personalization recommender systems, deep learning base, etc. has been increasing. Among NLP studies, sentiment analysis began to take shape in the mid-2000s as user review data increased. Sentiment analysis is a text classification task based on machine learning. The machine learning-based sentiment analysis has a disadvantage in that it is difficult to identify the review's information expression because it is challenging to consider the text's characteristics. In this study, we propose a deep learning recommender system that utilizes BERT's sentiment analysis by minimizing the disadvantages of machine learning. This study offers a deep learning recommender system that uses BERT's sentiment analysis by reducing the disadvantages of machine learning. The comparison model was performed through a recommender system based on Naive-CF(collaborative filtering), SVD(singular value decomposition)-CF, MF(matrix factorization)-CF, BPR-MF(Bayesian personalized ranking matrix factorization)-CF, LSTM, CNN-LSTM, GRU(Gated Recurrent Units). As a result of the experiment, the recommender system based on BERT was the best.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.127-138
• /
• 2011

The core service of most research portal sites is providing relevant research papers to various researchers that match their research interests. This kind of service may only be effective and easy to use when a user can provide correct and concrete information about a paper such as the title, authors, and keywords. However, unfortunately, most users of this service are not acquainted with concrete bibliographic information. It implies that most users inevitably experience repeated trial and error attempts of keyword-based search. Especially, retrieving a relevant research paper is more difficult when a user is novice in the research domain and does not know appropriate keywords. In this case, a user should perform iterative searches as follows : i) perform an initial search with an arbitrary keyword, ii) acquire related keywords from the retrieved papers, and iii) perform another search again with the acquired keywords. This usage pattern implies that the level of service quality and user satisfaction of a portal site are strongly affected by the level of keyword management and searching mechanism. To overcome this kind of inefficiency, some leading research portal sites adopt the association rule mining-based keyword recommendation service that is similar to the product recommendation of online shopping malls. However, keyword recommendation only based on association analysis has limitation that it can show only a simple and direct relationship between two keywords. In other words, the association analysis itself is unable to present the complex relationships among many keywords in some adjacent research areas. To overcome this limitation, we propose the hybrid approach for establishing association network among keywords used in research papers. The keyword association network can be established by the following phases : i) a set of keywords specified in a certain paper are regarded as co-purchased items, ii) perform association analysis for the keywords and extract frequent patterns of keywords that satisfy predefined thresholds of confidence, support, and lift, and iii) schematize the frequent keyword patterns as a network to show the core keywords of each research area and connecting keywords among two or more research areas. To estimate the practical application of our approach, we performed a simple experiment with 600 keywords. The keywords are extracted from 131 research papers published in five prominent Korean journals in 2009. In the experiment, we used the SAS Enterprise Miner for association analysis and the R software for social network analysis. As the final outcome, we presented a network diagram and a cluster dendrogram for the keyword association network. We summarized the results in Section 4 of this paper. The main contribution of our proposed approach can be found in the following aspects : i) the keyword network can provide an initial roadmap of a research area to researchers who are novice in the domain, ii) a researcher can grasp the distribution of many keywords neighboring to a certain keyword, and iii) researchers can get some idea for converging different research areas by observing connecting keywords in the keyword association network. Further studies should include the following. First, the current version of our approach does not implement a standard meta-dictionary. For practical use, homonyms, synonyms, and multilingual problems should be resolved with a standard meta-dictionary. Additionally, more clear guidelines for clustering research areas and defining core and connecting keywords should be provided. Finally, intensive experiments not only on Korean research papers but also on international papers should be performed in further studies.

• Knowledge Management Research
• /
• v.23 no.4
• /
• pp.315-338
• /
• 2022

In 1986, Korea established legal systems to support small and medium-sized start-ups, which becomes the main pillars of national development. The legal systems have stimulated start-up ecosystems to have more than 1 million new start-up companies founded every year during the past 30 years. To analyze the trend of Korea's start-up ecosystem, in this study, we collected 1.18 million news articles from 1991 to 2020. Then, we extracted news articles that have the keywords "start-up", "venture", and "start-up". We employed network analysis and topic modeling to analyze collected news articles. Our analysis can contribute to analyzing the government policy direction shown in the history of start-up support policy. Specifically, our analysis identifies the dynamic characteristics of government influenced by external environmental factors (e.g., society, economy, and culture). The results of our analysis suggest that the start-up ecosystems in Korea have changed and developed mainly by the government policies for corporation governance, industrial development planning, deregulation, and economic prosperity plan. Our frequency keyword analysis contributes to understanding entrepreneurial productivity attributed to activities among the networked components in industrial ecosystems. Our analyses and results provide practitioners and researchers with practical and academic implications that can help to establish dedicated support policies through forecast tasks of the economic environment surrounding the start-ups. Korean entrepreneurial productivity has been empowered by growing numbers of large companies in the mobile phone industry. The spectrum of large companies incorporates content startups, platform providers, online shopping malls, and youth-oriented start-ups. In addition, economic situational factors contribute to the growth of Korean entrepreneurial productivity the economic, which are related to the global expansions of the mobile industry, and government efforts to foster start-ups. Our research is methodologically implicative. We employ natural language processes for 30 years of media articles, which enables more rigorous analysis compared to the existing studies which only observe changes in government and policy based on a qualitative manner.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.