• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.67-86
• /
• 2020

Recommender Systems have been huge influence users and business more and more. Recently the importance of E-commerce has been reached rapid growth greatly in world-wide COVID-19 pandemic. Recommender system is the center of E-commerce lively. Top ranked E-commerce managers mentioned that recommender systems have a major influence on customer's purchase such as about 50% of Netflix, Amazon sales from their recommender systems. Most algorithms have been focused on improving accuracy of recommender system regardless of novelty, diversity, serendipity etc. Recommender systems with only high accuracy cannot satisfy business long-term profit because of generating sales polarization. In addition, customers do not experience enjoyment of shopping from only focusing accuracy recommender system because customer's preference is changed constantly. Therefore, recommender systems with various values need to be developed for user's high satisfaction. Reranking is the most useful methodology to realize diversity of recommender system. In this paper, diversity of recommender system is represented through constructing high similarity with users who have different preference using each user's purchased item's category algorithm. It is distinguished from past research approach which is changing the algorithm of recommender system without user's diversity preference level. We tried to discover user's diversity preference level and observed the results how the effect was different according to user's diversity preference level. In addition, graph-based recommender system was used to show diversity through user's network, not collaborative filtering. In this paper, Amazon Grocery and Gourmet Food data was used because the low-involvement product, such as habitual product, foods, low-priced goods etc., had high probability to show customer's diversity. First, a bipartite graph with users and items simultaneously is constructed to make graph-based recommender system. However, each users and items unipartite graph also need to be established to show diversity of recommender system. The weight of each unipartite graph has played crucial role changing Jaccard Distance of item's category. We can observe two important results from the user's unipartite network. First, the user's diversity preference level is observed from the network and second, dissimilar users can be discovered in the user's network. Through the research process, diversity of recommender system is presented highly with small accuracy loss and optimalization for higher accuracy is possible controlling diversity ratio. This paper has three important theoretical points. First, this research expands recommender system research for user's satisfaction with various values. Second, the graph-based recommender system is developed newly. Third, the evaluation indicator of diversity is made for diversity. In addition, recommender systems are useful for corporate profit practically and this paper has contribution on business closely. Above all, business long-term profit can be improved using recommender system with diversity and the recommender system can provide right service according to user's diversity level. Lastly, the corporate selling low-involvement products have great effect based on the results.

• Journal of Distribution Science
• /
• v.13 no.3
• /
• pp.51-60
• /
• 2015

Purpose - Among potential marketing strategies, the most efficient method to encourage purchase intention is through sales promotions. Sales promotions also serve to enhance customer satisfaction, which is closely related to the incidence of repurchases. Therefore, the success of retail stores greatly depends on the effectiveness of their promotional activities. The present study aimed to obtain the necessary information for apparel stores to establish more effective promotional activities. To this end, the study's specific research questions were to examine 1) consumer satisfaction with the recent sales promotions of retail apparel stores, 2) the levels of consumer preferences for different types of sales promotions (cash discounts, promotional gifts, prize drawings, discount coupons, stamp cards, or mileage cards), and 3) the differences in purchase intention according to preference levels for different types of sales promotions. Research design, data, and methodology - The research employed a descriptive survey method using a self-administered questionnaire. The sample consisted of 700 men (n=234) and women (n=466) ranging in age from their 20s to their 50s and residing in the Seoul area. Data were analyzed through methods including factor analysis as well as Cronbach's α coefficients, the t-test, ANOVA, and the Duncan test. Results - Differences among consumer preferences were identified for each type of sales promotion according to the purchase amount and the customer's age. In relation to purchase amounts below 500,000 won, participants in their 50s have lower preferences for price discounts than those in their 20s or 30s, whereas participants in their 40s or 50s have lower preferences for stamp cards and mileage cards than those in their 20s. When the purchase amount is greater than 500,000 won, housewives have higher preferences for promotional gifts than respondents with other occupations. However, no gender differences were found with regard to preference levels for the different types of sales promotions. Respondents generally exhibited mediocre satisfaction with the sales promotion events of retail apparel stores. They also expressed negative opinions about sales promotions when such promotions lead to high prices, as well as dissatisfaction with the poor quality of promotional gifts. It was also found that, regardless of the purchase amount, the groups with higher preferences for discount coupons and mileage cards displayed higher purchase intentions. Only when the purchase amount is greater than 200,000 won did the group with higher preferences for lottery system promotional gifts express higher purchase intentions. On the other hand, for all purchase amount sizes, there were no differences in purchase intentions according to preferences for cash discounts, promotional gifts, or stamp cards. Conclusions - The results revealed that greater effort must be devoted to enhancing consumers' satisfaction levels with the promotional activities performed by apparel retail stores. The results also showed that it is necessary to differentiate among sales promotion strategies according to preference levels for different types of sales promotions, purchase amounts, and target consumer ages.

• Journal of Distribution Science
• /
• v.12 no.2
• /
• pp.49-57
• /
• 2014

Purpose - Theorists and researchers in the area of customer satisfaction generally agree that product satisfaction intervenes between expectancy disconfirmation and various post-purchase cognitive states including attitude and behavioral intention. Studies in a variety of settings have supported the effect of expectation and its disconfirmation on satisfaction, but only a small number of studies address the cognitive consequences of satisfaction decisions and none report data on choice processes such as brand selection. This study examines the influence of satisfaction and its determinants on behavioral intention and product preference in eight coffee shops across the country. Generally it was found in both overall and summed attribute analyses that satisfaction was a function of expectation and disconfirmation, that intention was a function of satisfaction, and that preference was influenced by satisfaction and disconfirmation, the latter having the greater effect. Research design, data, and methodology - The main objective of this study was to assess the dimensions of consumer selection and satisfaction in choosing a coffee shop. In order to achieve this objective, a study of coffee shops across the country was conducted. This study comprised in-depth questionnaires distributed to coffee shop customers. A survey was conducted from September 1, 2011 to September 30, 2011, involving franchise coffee shop, independently owned coffee shop, and roastery coffee shop customers. Results - Hypothesis 1-1, which states that coffee shop choice attributes differ based on the type of coffee shop, is accepted. It has a significance level of 0.05, according to choosing properties of coffee shop by convenience of transportation, varieties of beans, residence of the owner (manager), information, and relationships. Hypothesis 1-2, which states that satisfaction with the choice factor differs depending on the type of coffee shops, is accepted. The P-values for cleanliness and varieties of beans were 0.04 and 0.00, respectively, and have a significance level of 0.05, according to the satisfaction with the chosen coffee shop. Hypothesis 2-1, which states that the importance of the choice attributes in coffee shop selections differs based on the demographic characteristics of the customers, is accepted. According to the t-test result, convenience of parking and residence of the owner (manager) are significant. Hypothesis 2-2, which states that satisfaction with the choice factor will differ depending of the type of coffee shop, is accepted. According to the t-test result, convenience of parking and residence of the owner (manager) are significant. Conclusions - This study has shown that intention to revisit a certain shop is most likely correlated to satisfaction in all cases. In order to offer subsequent developments for coffee shops, this study also identifies relations between customer satisfaction and selection by finding significant factors. In order to maximize customers' satisfaction, coffee shops should analyze and satisfy customers' needs and wants in terms of coffee service. While the findings do not generalize beyond the mall sampling procedure used here, we have hopefully identified a close approximation of the process of satisfaction decisions used by consumers generally.

• Journal of Distribution Science
• /
• v.7 no.2
• /
• pp.89-119
• /
• 2009

The purpose of this research is showing an appropriate way of maximizing customer service and establishing VOC system by analyzing different voices from complaining customers as well as loyal customers. This research is also aimed at figuring out how companies can implement effective service marketing methods in the field complying with customers' needs and how they can survive in the competition. The range of research is confined to 5 marketing companies and their web-sites on which customers can get logged and directly post their claims. These web-sites showed how those 5 companies cope with customer claims. A questionnaire research was made in A's store to evaluate customer satisfaction. These are conclusions drawn by this research. First, prompt reactions of sincerity to customers' claims contribute to building favorable corporate images. Second, the preference to VOC channels varies with age and sex. Marketers should implement respectively different channels for customers under age 30 and those over age 40. Women have a tendency to prefer instant phone conversations and want to have their claims well listened to. Third, a series of shift in customer trend drives companies into establishing their own interactive VOC systems based on customers' preferences. Customer-oriented management has become a key factor for survival in recent intensely competitive market situation, as the web-based e-commerce market has been rapidly growing accompanied with a dramatic advance of network marketing methods. This research suggests some practical methods to establish a customer-oriented VOC system that can be easily adopted in the field.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.115-130
• /
• 2011

Many online stores bring features that can build trust in their customers. More so, the number of products or content services on online stores has been increasing rapidly. Hence, personalization on online stores is considered to be an important technology to companies and customers. Recommender systems that provide favorable products and customer product reviews to users are the most commonly used features in this purpose. There are many studies to that investigated the relationship between social presence as an antecedent of trust and provision of recommender systems or customer product reviews. Many online stores have made efforts to increase perceived social presence of their customers through customer reviews, recommender systems, and analyzing associations among products. Primarily because social presence can increase customer trust or reuse intention for online stores. However, there were few studies that investigated the interactions between recommendation type, product type and provision of customer product reviews on social presence. Therefore, one of the purposes of this study is to identify the effects of personalized recommender systems and compare the role of customer reviews with product types. This study performed an experiment to see these interactions. Experimental web pages were developed with $2{\times}2$ factorial setting based on how to provide social presence to users with customer reviews and two product types such as hedonic and utilitarian. The hedonic type was a ringtone chosen from Nate.com while the utilitarian was a TOEIC study aid book selected from Yes24.com. To conduct the experiment, web based experiments were conducted for the participants who have been shopping on the online stores. Participants were a total of 240 and 30% of the participants had the chance of getting the presents. We found out that social presence increased for hedonic products when personalized recommendations were given compared to non.personalized recommendations. Although providing customer reviews for two product types did not significantly increase social presence, provision of customer product reviews for hedonic (ringtone) increased perceived social presence. Otherwise, provision of customer product reviews could not increase social presence when the systems recommend utilitarian products (TOEIC study.aid books). Therefore, it appears that the effects of increasing perceived social presence with customer reviews have a difference for product types. In short, the role of customer reviews could be different based on which product types were considered by customers when they are making a decision related to purchasing on the online stores. Additionally, there were no differences for increasing perceived social presence when providing customer reviews. Our participants might have focused on how recommendations had been provided and what products were recommended because our developed systems were providing recommendations after participants rating their preferences. Thus, the effects of customer reviews could appear more clearly if our participants had actual purchase opportunity for the recommendations. Personalized recommender systems can increase social presence of customers more than nonpersonalized recommender systems by using user preference. Online stores could find out how they can increase perceived social presence and satisfaction of their customers when customers want to find the proper products with recommender systems and customer reviews. In addition, the role of customer reviews of the personalized recommendations can be different based on types of the recommended products. Even if this study conducted two product types such as hedonic and utilitarian, the results revealed that customer reviews for hedonic increased social presence of customers more than customer reviews for utilitarian. Thus, online stores need to consider the role of providing customer reviews with highly personalized information based on their product types when they develop the personalized recommender systems.

• Journal of Fashion Business
• /
• v.16 no.5
• /
• pp.114-129
• /
• 2012

The purpose of this study is to analyze the effects of consumer's need for uniqueness, whether or not using ALPHA-NUMERIC Brand Name and types of fashion goods upon the consumer's attitude. The experimental design of this study is three-ways complex factors design of 2 (Consumer's Need for Uniqueness : High vs Law) ${\times}$ 2 (Whether or not to use ALPHA-NUMERIC Brand Name : Used brand vs Non-used brand) ${\times}$ 2 (Types of fashion goods: Rational fashion goods vs Emotional fashion goods) The conclusions are as follows. 1. The interaction effect upon a favorite level according to consumer's need for uniqueness, whether or not using ALPHA-NUMERIC brand name and types of fashion goods upon the consumer's attitude is proven significant. For the group where customer's need for uniqueness is low, when ALPHA-NUMERIC brand name is not used, the favorableness of rational fashion good, a parka is lower than that of emotional fashion good, one-piece dress. However, there is no significant difference in favorableness by types of fashion goods when ALPHA-NUMERIC brand name is used. At the group with high need for uniqueness, while there is no significant difference in favorableness when ALPHA-NUMERIC brand name is not used, the favorableness of parka is higher than that of one-piece dress when ALPHA-NUMERIC brand name is used. 2. The interaction effects upon purchase intention according to consumer's need for uniqueness, whether or not using ALPHA-NUMERIC brand name and types of fashion goods are proven significant. For the group where customer's need for uniqueness is low, there is no significant different in the favorableness whether or not ALPHA-NUMERIC brand name is used. On the other hand, the group with high need for uniqueness, if ALPHA-NUMERIC brand name is used, the intention to purchase parka is higher than the intention to purchase one-piece dress.

• Journal of Distribution Science
• /
• v.14 no.11
• /
• pp.61-73
• /
• 2016

Purpose - Marketing scholars have developed various types of mathematical models for describing marketing phenomenon, because there is no single model comprehensive enough to incorporate all the relevant marketing phenomena. This study tries to summarize the behavioral foundations and the mathematical derivations of the most widely used marketing models and discusses their strategic implications. This study selected four representative marketing models: multinomial logit(MNL) model, elimination-by-aspects(EBA) model, Hauser and Shugan model and Bass diffusion model. Especially, this study focuses on Hauser and Shugan(1983)'s Defender model and discusses the model's behavioral foundation and its implications. Research design, data, and methodology - Of the four selected model, the multinomial logit model is selected as the basic normative model and the other three models are described as descriptive models in contrast. Starting the discussion from the multinomial logit model, this study explains what important strategic variables are incorporated in each of the four models. The IIA(independence of irrelevant alternatives) axiom and Luce choice model is also discussed in relation to the multinomial logit model. The concept of 'efficient frontier' is discussed in relation to Hauser and Shugan's model. Graphs and tables are used to represent the key implications. No empirical study is included. Results - The analyses of the mathematical marketing models are shown to be very useful in understanding the essence of positioning strategy. The multinomial logit model implies the importance of increasing utility or consumer preference level. The EBA model implies the importance of lowering the inter-brand similarity and dominating the competitors. Hauser and Shugan model implies the importance of considering customer heterogeneity distribution in selecting the target market. Conclusions - It is shown that the concepts of 'efficient frontier' is useful in understanding the effectiveness of positioning strategy. Market positioning can be understood as occupying some place on the efficient frontier. The important strategic implications can be summarized as follows: Always try to increase customer preference by providing what they value, and differentiate from competing alternatives as much as possible. The best positioning strategy is to dominate all the competitors and the worst is to be dominated by the competitors.

• Food Science and Preservation
• /
• v.14 no.1
• /
• pp.105-108
• /
• 2007

This study tested customer preferences for "Fuji" apples stored using functional modified atmosphere film (30m) for 16 weeks at $0^{\circ}C$. Customers were 20-60 years of age and lived in either Seoul or Geochang. The freshness, texture, chewiness, and purchase attractiveness of apples in film packaging were judged to be significantly higher than control apples by those aged 20-29 years. The freshness, sourness, flavor, and purchase attractiveness of apples in film packaging were judged to be significantly higher than control apples by those aged 30-39 years. The flavor and sweetness of apples in film packag ing were judged to be significantly higher than control apples by those aged either 40-49 or 50-59 years (${\alpha}=0.05$). In the overall preference tests, apple freshness (P=0.0011), apple flavor (P=0.0002), and apple purchase attractiveness (P=0.0018) of apples in film packaging were judged to be significantly better than control apples by all age groups (those aged 20-59 years).

• The Journal of the Korea Contents Association
• /
• v.10 no.3
• /
• pp.282-293
• /
• 2010

Currently, due to the rapid growth of Internet businesses, competition is deepening even in Internet portal markets. In markets where competition is severe, companies can no longer hold a competitive advantage if they cannot deliver their own distinguished, unique images to customers. Therefore, this research planned to establish distinguished positioning strategies by comparing competition relationships among portals which go through building positioning maps and understanding the evaluation attributes and ideal points of internal portal images preferred by segmented customer groups. College students who are heavy users of the Internet were selected as research subjects, and they were led to make an evaluation of the image of Internet portals they mainly use. The analysis result showed that attributes distinguished the most among portals were entertainment, additional service, and convenience while the attribute distinguished the least was customer service. Moreover, understanding of preference and ideal points regarding portals also showed significant differences by segmented groups. Such research results are expected to become meaningful raw data in regards to building distinguished market segment strategies in Internet portal markets.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.2
• /
• pp.227-233
• /
• 2004

Complex scheduling problems are related to planning, scheduling, constraint satisfaction problems, object-oriented concepts, and agent systems. Human preference-driven scheduling technique was to solve complex scheduling problems using constraint satisfaction problems and object-oriented concepts. We have tried to apply human preference-driven scheduling technique to reservation problems. For customer's satisfaction, we have considered customer's preferences in the reservation scheduling. The technique of reservation scheduling proposed in this thesis is based on object-oriented concepts. 1'o consider the over all satisfaction, the events of every object are alloted to the board along its priority. Constraints to reservation scheduling are classified to global and local. The definition of board and information of every event are global constraints and the preferences to object's board slots are local constraints. We have applied look-ahead technology to reservation scheduling in order to minimize backtracking not to fail the allotment of events.