• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.424-428
• /
• 1997

본 논문에서는 사용자가 원하는 분위기의 칼라패턴을 추천하여 주는 칼라패턴 데이터 베이스 시스템을 제안하였다. 사용자가 원하는 분위기는 감각언어로 나타낼 수 있는데, 이 감각 언어를 이용한 9가지 심리적 척도의 감성 질의의 형태로 시스템에 입력되며 시스템은 입력된 질의와 칼라패턴의 감성 속성을 비교하여 사용자가 원하는 분위기의 칼라패턴을 추천한다. 이를 위하여 감각 언어의 9가지 실리적 척도에 대한 칼라패텬의 9가지으 감성 속성을 신경회로망을 이용하여 추출하였다. 칼라패턴 데이터 베이스 시스템은 패션 및 상품 디자인, 화랑의 회화 등의 데이터 베이스에서 소비자들의 요구에 좀 더 빠르게 접근하는 해결책을 제공해 줄 수 있을 것이다.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.23-51
• /
• 2003

With the recent expansion of internet shopping mall, the importance of intelligent products recommendation agents has been increasing. for the products recommendation, This paper propose case-based reasoning approach, and developed a case-based bundle products recommendation system which can recommend a set of sea food used in family events. To apply CBR approach to the bundle products recommendation, it requires the following 4R steps : \circled1 Retrieval, \circled2 Reuse, \circled3 Revise, \circled4 Retain. To retrieve similar cases from the case-base efficiently, case representation scheme is most important. This paper used OW(Object Modeling Technique) to represent bundle products recommendation cases, and developed a similarity measure method to search similar cases. To measure similarity, we used weight-sum approach basically. Especially This paper propose the meaning and uses of taxonomies for representing case features.

• Journal of Intelligence and Information Systems
• /
• v.15 no.4
• /
• pp.183-200
• /
• 2009

Collaborative Filtering is one of the most used recommender systems. However, basically it cannot be used to recommend new products to customers because it finds products only based on the purchasing history of each customer. In order to cope with this shortcoming, many researchers have proposed the hybrid recommender system, which is a combination of collaborative filtering and content-based filtering. Content-based filtering recommends the products whose attributes are similar to those of the products that the target customers prefer. However, the hybrid method is used only for the limited categories of products such as music and movie, which are the products whose attributes are easily extracted. Therefore it is essential to find a more effective approach to recommend to customers new products in any category. In this study, we propose a new recommendation method which applies centrality concept widely used to analyze the relational and structural characteristics in social network analysis. The new products are recommended to the customers who are highly likely to buy the products, based on the analysis of the relationships among products by using centrality. The recommendation process consists of following four steps; purchase similarity analysis, product network construction, centrality analysis, and new product recommendation. In order to evaluate the performance of this proposed method, sales data from H department store, one of the well.known department stores in Korea, is used.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.7
• /
• pp.263-270
• /
• 2014

This paper suggests a method for predicting a box-office success of the film. Lately, as the growth of the film industry, a variety of studies for the prediction of market demand is being performed. The product life cycle of film is relatively short cultural goods. Therefore, in order to produce stable profits, marketing costs before opening as well as the number of screen after opening need a plan. To fulfill this plan, the demand for the product and the calculation of economic profit scale should be preceded. The cases of existing researches, as a variable for predicting, primarily use the factors of competition of the market or the properties of the film. However, the proportion of the potential audiences who purchase the goods is relatively insufficient. Therefore, in this paper, in order to consider people's perception of a movie, Twitter was utilized as one of the survey samples. The existing variables and the information extracted from Twitter are defined as off-line and on-line element, and applied those two elements in machine learning by combining. Through the experiment, the proposed predictive techniques are validated, and the results of the experiment predicted the chance of successful film with about 95% of accuracy.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.6
• /
• pp.684-695
• /
• 2001

Recent recommender system uses a method of combining collaborative filtering system and content based filtering system in order to solve sparsity and first rater problem in collaborative filtering system. Collaborative filtering systems use a database about user preferences to predict additional topics. Content based filtering systems provide recommendations by matching user interests with topic attributes. In this paper, we describe a method for discovery of user preference through combining two techniques for recommendation that allows the application of machine learning algorithm. The proposed collaborative filtering method clusters user using genetic algorithm based on items categorized by Naive Bayes classifier and the content based filtering method builds user profile through extracting user interest using relevance feedback. We evaluate our method on a large database of user ratings for web document and it significantly outperforms previously proposed methods.

• Journal of Digital Convergence
• /
• v.17 no.3
• /
• pp.161-168
• /
• 2019

The purpose of this study analyze consumer usage characteristics and product development guide of electronic pen based on TAM theory(Davies, 1989). Research methods apply contents analysis(qualitative research) and Activity/Inactivity analysis of main consumer participation. Research results are as follows. Active consumer indicated 30-49 age, male, office job and research fellow. And they suggested stable power supply system, App connected pen function extension, add the modified pen function, advanced data recognition of pen, advanced take note ability and stable grip feeling of pen, selected line width, synchronization improvement with other smart device and charging function. These result indicated the importance product improvement diffusion factor of early market to main market. The future research of electric pen focused on different product strategy between electric pen and smart device connected electric pen.

• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.111-126
• /
• 2017

Recommender systems based on association rule mining significantly contribute to seller's sales by reducing consumers' time to search for products that they want. Recommendations based on the frequency of transactions such as orders can effectively screen out the products that are statistically marketable among multiple products. A product with a high possibility of sales, however, can be omitted from the recommendation if it records insufficient number of transactions at the beginning of the sale. Products missing from the associated recommendations may lose the chance of exposure to consumers, which leads to a decline in the number of transactions. In turn, diminished transactions may create a vicious circle of lost opportunity to be recommended. Thus, initial sales are likely to remain stagnant for a certain period of time. Products that are susceptible to fashion or seasonality, such as clothing, may be greatly affected. This study was aimed at expanding association rules to include into the list of recommendations those products whose initial trading frequency of transactions is low despite the possibility of high sales. The particular purpose is to predict the strength of the direct connection of two unconnected items through the properties of the paths located between them. An association between two items revealed in transactions can be interpreted as the interaction between them, which can be expressed as a link in a social network whose nodes are items. The first step calculates the centralities of the nodes in the middle of the paths that indirectly connect the two nodes without direct connection. The next step identifies the number of the paths and the shortest among them. These extracts are used as independent variables in the regression analysis to predict future connection strength between the nodes. The strength of the connection between the two nodes of the model, which is defined by the number of nodes between the two nodes, is measured after a certain period of time. The regression analysis results confirm that the number of paths between the two products, the distance of the shortest path, and the number of neighboring items connected to the products are significantly related to their potential strength. This study used actual order transaction data collected for three months from February to April in 2016 from an online commerce company. To reduce the complexity of analytics as the scale of the network grows, the analysis was performed only on miscellaneous goods. Two consecutively purchased items were chosen from each customer's transactions to obtain a pair of antecedent and consequent, which secures a link needed for constituting a social network. The direction of the link was determined in the order in which the goods were purchased. Except for the last ten days of the data collection period, the social network of associated items was built for the extraction of independent variables. The model predicts the number of links to be connected in the next ten days from the explanatory variables. Of the 5,711 previously unconnected links, 611 were newly connected for the last ten days. Through experiments, the proposed model demonstrated excellent predictions. Of the 571 links that the proposed model predicts, 269 were confirmed to have been connected. This is 4.4 times more than the average of 61, which can be found without any prediction model. This study is expected to be useful regarding industries whose new products launch quickly with short life cycles, since their exposure time is critical. Also, it can be used to detect diseases that are rarely found in the early stages of medical treatment because of the low incidence of outbreaks. Since the complexity of the social networking analysis is sensitive to the number of nodes and links that make up the network, this study was conducted in a particular category of miscellaneous goods. Future research should consider that this condition may limit the opportunity to detect unexpected associations between products belonging to different categories of classification.

• Journal of Global Scholars of Marketing Science
• /
• v.17 no.1
• /
• pp.51-75
• /
• 2007

Dongdaemun fashion market has been successfully positioned as a main hub for non-brand fashion product distribution in Korea. One of important competitive advantages of Dongdaemun market often quoted by retail researchers is an efficiently managed network system among supply chain members. This study aimed to examine the importance of buyer-supplier relationship elements and supplier properties from buyers' perspectives (small & very small-sized fashion stores in Dongdaemun market), and to identify the determinants of the relationship length between suppliers and buyers. Survey responses of 233 stores were analyzed using EQS 6.1 for Window and SPSSWIN 10.0. The findings could be summarized as follows: First, fashion stores perceived that right delivery as the most important factor, and geographically closeness, design capability, quality, and lower price followed in order. Second, the characteristics of stores such as location, wholesaling versus retailing focusing, monthly sales, and total business length all affected the perceived importance of buyer-supplier relationship. Third, design capacity, communication, power was identified as determinants of actual relationship length with a supplier, while communication and trust were found to be determinants of future expected relationship length.

• The KIPS Transactions:PartD
• /
• v.18D no.4
• /
• pp.237-244
• /
• 2011

Opinion Mining summarizes with classifying sensitive opinions of customers in huge online customer reviews for the attributes of products or services by positive and negative opinions. Because the customers represent their interests through subjective opinions as well as objective facts, the existing opinion mining techniques, which can analyze just the sensitive opinions, need to be expanded.. In this paper, We propose the novel entity association network model which expands the existing opinion mining techniques. The entity association model can not only represent positive and negative degree of the sensitive opinions, but also can represent the degree of the associations and relative importances between entities. We designed and implemented the customer reviews analysis system based on the entity association network model. We recognized that the system can represent more abundant information than the existing opinion mining techniques.