• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.609-625
• /
• 2022

Validation of satellite data products is critical for subsequent analysis that is based on the data. Particularly, performance of ocean color products in turbid and shallow near-land ocean areas has been questioned for long time for its difficulty that stems from the complex optical environment with varying distribution of water constituents. Furthermore, validation with ship-based or station-based measurements has also exhibited clear limitation in its spatial scale that is not compatible with that of satellite data. This study firstly performed validation of major GOCI-II products such as remote sensing reflectance, chlorophyll-a concentration, suspended particulate matter, and colored dissolved organic matter, using the in-situ measurements collected from ship-based field campaign. Secondly, this study also presents preliminary analysis on the use of drone images for product validation. Multispectral images were acquired from a MicaSense RedEdge camera onboard a UAV to compensate for the significant scale difference between the ship-based measurements and the satellite data. Variation of water radiance in terms of camera altitude was analyzed for future application of drone images for validation. Validation conducted with a limited number of samples showed that GOCI-II remote sensing reflectance at 555 nm is overestimated more than 30%, and chlorophyll-a and colored dissolved organic matter products exhibited little correlation with in-situ measurements. Suspended particulate matter showed moderate correlation with in-situ measurements (R²~0.6), with approximately 20% uncertainty.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.263-286
• /
• 2022

This study acquires NBA statistical information for a total of 32 years from 1990 to 2022 using web crawling, observes variables of interest through exploratory data analysis, and generates related derived variables. Unused variables were removed through a purification process on the input data, and correlation analysis, t-test, and ANOVA were performed on the remaining variables. For the variable of interest, the difference in the mean between the groups that advanced to the playoffs and did not advance to the playoffs was tested, and then to compensate for this, the average difference between the three groups (higher/middle/lower) based on ranking was reconfirmed. Of the input data, only this year's season data was used as a test set, and 5-fold cross-validation was performed by dividing the training set and the validation set for model training. The overfitting problem was solved by comparing the cross-validation result and the final analysis result using the test set to confirm that there was no difference in the performance matrix. Because the quality level of the raw data is high and the statistical assumptions are satisfied, most of the models showed good results despite the small data set. This study not only predicts NBA game results or classifies whether or not to advance to the playoffs using machine learning, but also examines whether the variables of interest are included in the major variables with high importance by understanding the importance of input attribute. Through the visualization of SHAP value, it was possible to overcome the limitation that could not be interpreted only with the result of feature importance, and to compensate for the lack of consistency in the importance calculation in the process of entering/removing variables. It was found that a number of variables related to three points and errors classified as subjects of interest in this study were included in the major variables affecting advancing to the playoffs in the NBA. Although this study is similar in that it includes topics such as match results, playoffs, and championship predictions, which have been dealt with in the existing sports data analysis field, and comparatively analyzed several machine learning models for analysis, there is a difference in that the interest features are set in advance and statistically verified, so that it is compared with the machine learning analysis result. Also, it was differentiated from existing studies by presenting explanatory visualization results using SHAP, one of the XAI models.

• The Journal of KAIRB
• /
• v.2 no.2
• /
• pp.37-48
• /
• 2020

Purpose: The purpose of this study is to assess the operational status and level of understanding among IRB and HRPP staffs at a hospital or a research institute to the HRPP guideline set by the Ministry of Food and Drug Safety (MFDS) and to provide recommendations. Methods: Online survey was distributed among members of Korean Association of IRB (KAIRB) through each IRB office. The result was separated according to topic and descriptive statistics was used for analysis. Result: Survey notification was sent out to 176 institutions and 65 (37.1%) institutions answered the survey by online. Of 65 institutions that answered the survey; 83.1% was hospital, 12.3% was university, 3.1% was medical college, 1.5% was research institution. 23 institutions (25.4%) established independent HRPP offices and 39 institutions (60.0%) did not. 12 institutions (18.5%) had separate IRB and HRPP heads, 21 (32.3%) institutions separated business reporting procedure and person in charge, 12 institutions separated the responsibility of IRB and HRPP among staff, and 45 institutions (69.2%) had audit & non-compliance managers. When asked about the most important basic task for HRPP, 23% answered self-audit. And according to 43.52%, self-audit was also the most by both institutions that operated HRPP and institutions that did not. When basic task performance status was analyzed, on average, the institutions that operated HRPP was 14% higher than institutions that only operated IRB. 9 (13.8%) institutions were evaluated and obtained HRPP accreditation from MFDS and the most common reason for obtaining the accreditation was to be selected as Institution for the education of persons conducting clinical trial (6 institutions). The most common reason for not obtaining HRPP accreditation was because of insufficient staff and limited capacity of the institution (28%). Institutions with and without a plan to be HRPP accredited by MFDS were 20 (37.7%) each. 34 institutions (52.3%) answered HRPP evaluation method and accreditation by MFDS was appropriate while 31 institutions (47.7%) answered otherwise. 36 institutions answered that HRPP evaluation and accreditation by MFDS was credible while 29 institutions (44.5%) answered that HRPP evaluation method and accreditation by MFDS was not credible. Conclusion: 1. MFDS's HRPP accreditation program can facilitate the main objective of HRPP and MFDS's HRPP accreditation program should be encouraged to non-tertiary hospitals by taking small staff size into consideration and issuing accreditation by segregating accreditation. 2. While issuing Institution for the education of persons conducting clinical trial status as a benefit of MFDS's HRPP accreditation program, it can also hinder access to MFDS's HRPP accreditation program. It should also be considered that the non-contact culture during COVID-19 pandemic eliminated time and space limitation for education. 3. For clinical research conducted internally by an institution, internal audit is the most effective and sole method of protecting safety and right of the test subjects and integrity for research in Korea. For this reason, regardless of the size of the institution, an internal audit should be enforced. 4. It is necessary for KAIRB and MFDSto improve HRPP awareness by advocating and educating the concept and necessity of HRPP in clinical research. 5. A new HRPP accreditation system should be setup for all clinical research with human subjects, including Investigational New Drug (IND) application in near future.

• Asia Marketing Journal
• /
• v.13 no.3
• /
• pp.79-102
• /
• 2011

Researchers in channel dyads have devoted much attention to relationship between interdependence (i.e. interdependence enymmetry and total interdependence) and conflict that promote channel performance. In social science, in spite of the inconsistent results in marketing practice, there are two contradictory theories explain the relationship between interdependence and conflict - bilateral deterrence theory and conflict spiral theory. The authors apply these theories to co-marketing alliance situation in terms that this relationship is also incorporated both company's dependence, either from one company's perspective or each partner about its respective dependence. Using survey data and archival data from 181 companies enlisted in a telecommunication membership program, the authors find out the relationship between interdependence and conflict as well as investigate the antecedents of interdependence - transaction age, transaction frequency, the numbers of alliance partner, and co-marketing alliance specific assets according to previous researches. Using PLS analysis, the authors demonstrate that, with increasing total interdependence in a telecommunication membership program, two co-marketing partners' conflict level is increased in accord with the author's conflict spiral theory predictions. As expected, higher interdependence asymmetry has negative value to level of conflict even though this result is not statistically significant. Other findings can be summarized as follows. In the perspective of telecommunication company, transaction age, transaction frequency, and co-marketing alliance specific assets have influence on its dependence on a partner as independent variables. To the contrary, in a partner's perspective, transaction frequency, co-marketing alliance specific assets and the numbers of alliance partner have significantly impact on its dependence on a telecommunication company. In direct effect analysis, it is shown that transaction age, frequency and co-marketing alliance specific assets have direct influence on conflict. This results suggest that it is more useful for a telecommunication company to select a co-marketing partner which is frequently used by customers and earned high rates of mileage. In addition, the results show that dependence of a telecommunication company on a co-marketing partner is more significantly effected to co-marketing alliance conflict than partner's one. It provide an effective conflict management strategy to a telecommunication company for controling customer's usage rate or having the co-marketing partner deposit high level of alliance specific investment (i.e. mileage). To a co-marketing partner of telecommunication company, it is required control the percentage of co-marketing sales in total sales revenue or seek various co-marketing partners in order for co-marketing conflict management. The research implications, limitation and future research of these results are discussed.

• Journal of Distribution Research
• /
• v.17 no.1
• /
• pp.87-115
• /
• 2012

Introduction: In these days, a loyalty program is one of the most common marketing mechanisms (Lacey & Sneath, 2006; Nues & Dreze, 2006; Uncles et al., 20003). In recent years, Coalition Loyalty Program is more noticeable as one of progressed forms. In the past, loyalty program was operating independently by single product brand or single retail channel brand. Now, companies using Coalition Loyalty Program share their programs as one single service and companies to participate to this program continue to have benefits from their existing program as well as positive spillover effect from the other participating network companies. Instead of consumers to earn or spend points from single retail channel or brand, consumers will have more opportunities to utilize their points and be able to purchase other participating companies products. Issues that are related to form of loyalty programs are essentially connected with consumers' perceived view on convenience of using its program. This can be a problem for distribution companies' strategic marketing plan. Although Coalition Loyalty Program is popular corporate marketing strategy to most companies, only few researches have been published. However, compared to independent loyalty program, coalition loyalty program operated by third parties of partnership has following conditions: Companies cannot autonomously modify structures of program for individual companies' benefits, and there is no guarantee to operate and to participate its program continuously by signing a contract. Thus, it is important to conduct the study on how coalition loyalty program affects companies' success and its process as much as conducting the study on effects of independent program. This study will complement the lack of coalition loyalty program study. The purpose of this study is to find out how consumer loyalty affects affiliated brands, its cause and mechanism. The past study about loyalty program only provided the variation of performance analysis, but this study will specifically focus on causes of results. In order to do these, this study is designed and to verify three primary objects as following; First, based on opinions of Switching Barriers (Fornell, 1992; Ping, 1993; Jones, et at., 2000) about causes of loyalty of coalition brand, 'brand attractiveness' and 'brand switching cost' are antecedents and causes of change in 'brand loyalty' will be investigated. Second, influence of consumers' perception and attitude prior to joining coalition loyalty program, influence of program in retail brands, brand attractiveness and spillover effect of switching cost after joining coalition program will be verified. Finally, the study will apply 'prior brand preference' as a variable and will provide a relationship between effects of coalition loyalty program and prior preference level. Hypothesis Hypothesis 1. After joining coalition loyalty program, more preferred brand (compared to less preferred brand) will increase influence on brand attractiveness to brand loyalty. Hypothesis 2. After joining coalition loyalty program, less preferred brand (compared to more preferred brand) will increase influence on brand switching cost to brand loyalty. Hypothesis 3. (1)Brand attractiveness and (2)brand switching cost of more preferred brand (before joining the coalition loyalty program) will influence more positive effects from (1)program attractiveness and (2)program switching cost of coalition loyalty program (after joining) than less preferred brand. Hypothesis 4. After joining coalition loyalty program, (1)brand attractiveness and (2)brand switching cost of more preferred brand will receive more positive impacts from (1)program attractiveness and (2)program switching cost of coalition loyalty program than less preferred brand. Hypothesis 5. After joining coalition loyalty program, (1)brand attractiveness and (2)brand switching cost of more preferred brand will receive less impacts from (1)brand attractiveness and (2)brand switching cost of different brands (having different preference level), which joined simultaneously, than less preferred brand. Method : In order to validate hypotheses, this study will apply experimental method throughout virtual scenario of coalition loyalty program if consumers have used or available for the actual brands. The experiment is conducted twice to participants. In a first experiment, the study will provide six coalition brands which are already selected based on prior research. The survey asked each brand attractiveness, switching cost, and loyalty after they choose high preference brand and low preference brand. One hour break was provided prior to the second experiment. In a second experiment, virtual coalition loyalty program "SaveBag" was introduced to participants. Participants were informed that "SaveBag" will be new alliance with six coalition brands from the first experiment. Brand attractiveness and switching cost about coalition program were measured and brand attractiveness and switching cost of high preference brand and low preference brand were measured as same method of first experiment. Limitation and future research This study shows limitations of effects of coalition loyalty program by using virtual scenario instead of actual research. Thus, future study should compare and analyze CLP panel data to provide more in-depth information. In addition, this study only proved the effectiveness of coalition loyalty program. However, there are two types of loyalty program, which are Single and Coalition, and success of coalition loyalty program will be dependent on market brand power and prior customer attitude. Therefore, it will be interesting to compare effects of two programs in the future.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.79-96
• /
• 2012

As the pace of competition dramatically accelerates and the complexity of change grows, a variety of research have been conducted to improve firms' short-term performance and to enhance firms' long-term survival. In particular, researchers and practitioners have paid their attention to identify promising technologies that lead competitive advantage to a firm. Discovery of promising technology depends on how a firm evaluates the value of technologies, thus many evaluating methods have been proposed. Experts' opinion based approaches have been widely accepted to predict the value of technologies. Whereas this approach provides in-depth analysis and ensures validity of analysis results, it is usually cost-and time-ineffective and is limited to qualitative evaluation. Considerable studies attempt to forecast the value of technology by using patent information to overcome the limitation of experts' opinion based approach. Patent based technology evaluation has served as a valuable assessment approach of the technological forecasting because it contains a full and practical description of technology with uniform structure. Furthermore, it provides information that is not divulged in any other sources. Although patent information based approach has contributed to our understanding of prediction of promising technologies, it has some limitations because prediction has been made based on the past patent information, and the interpretations of patent analyses are not consistent. In order to fill this gap, this study proposes a technology forecasting methodology by integrating patent information approach and artificial intelligence method. The methodology consists of three modules : evaluation of technologies promising, implementation of technologies value prediction model, and recommendation of promising technologies. In the first module, technologies promising is evaluated from three different and complementary dimensions; impact, fusion, and diffusion perspectives. The impact of technologies refers to their influence on future technologies development and improvement, and is also clearly associated with their monetary value. The fusion of technologies denotes the extent to which a technology fuses different technologies, and represents the breadth of search underlying the technology. The fusion of technologies can be calculated based on technology or patent, thus this study measures two types of fusion index; fusion index per technology and fusion index per patent. Finally, the diffusion of technologies denotes their degree of applicability across scientific and technological fields. In the same vein, diffusion index per technology and diffusion index per patent are considered respectively. In the second module, technologies value prediction model is implemented using artificial intelligence method. This studies use the values of five indexes (i.e., impact index, fusion index per technology, fusion index per patent, diffusion index per technology and diffusion index per patent) at different time (e.g., t-n, t-n-1, t-n-2, ${\cdots}$) as input variables. The out variables are values of five indexes at time t, which is used for learning. The learning method adopted in this study is backpropagation algorithm. In the third module, this study recommends final promising technologies based on analytic hierarchy process. AHP provides relative importance of each index, leading to final promising index for technology. Applicability of the proposed methodology is tested by using U.S. patents in international patent class G06F (i.e., electronic digital data processing) from 2000 to 2008. The results show that mean absolute error value for prediction produced by the proposed methodology is lower than the value produced by multiple regression analysis in cases of fusion indexes. However, mean absolute error value of the proposed methodology is slightly higher than the value of multiple regression analysis. These unexpected results may be explained, in part, by small number of patents. Since this study only uses patent data in class G06F, number of sample patent data is relatively small, leading to incomplete learning to satisfy complex artificial intelligence structure. In addition, fusion index per technology and impact index are found to be important criteria to predict promising technology. This study attempts to extend the existing knowledge by proposing a new methodology for prediction technology value by integrating patent information analysis and artificial intelligence network. It helps managers who want to technology develop planning and policy maker who want to implement technology policy by providing quantitative prediction methodology. In addition, this study could help other researchers by proving a deeper understanding of the complex technological forecasting field.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.73-92
• /
• 2014

An Adaptive Clustering-based Collaborative Filtering Technique was proposed to solve the fundamental problems of collaborative filtering, such as cold-start problems, scalability problems and data sparsity problems. Previous collaborative filtering techniques were carried out according to the recommendations based on the predicted preference of the user to a particular item using a similar item subset and a similar user subset composed based on the preference of users to items. For this reason, if the density of the user preference matrix is low, the reliability of the recommendation system will decrease rapidly. Therefore, the difficulty of creating a similar item subset and similar user subset will be increased. In addition, as the scale of service increases, the time needed to create a similar item subset and similar user subset increases geometrically, and the response time of the recommendation system is then increased. To solve these problems, this paper suggests a collaborative filtering technique that adapts a condition actively to the model and adopts the concepts of a context-based filtering technique. This technique consists of four major methodologies. First, items are made, the users are clustered according their feature vectors, and an inter-cluster preference between each item cluster and user cluster is then assumed. According to this method, the run-time for creating a similar item subset or user subset can be economized, the reliability of a recommendation system can be made higher than that using only the user preference information for creating a similar item subset or similar user subset, and the cold start problem can be partially solved. Second, recommendations are made using the prior composed item and user clusters and inter-cluster preference between each item cluster and user cluster. In this phase, a list of items is made for users by examining the item clusters in the order of the size of the inter-cluster preference of the user cluster, in which the user belongs, and selecting and ranking the items according to the predicted or recorded user preference information. Using this method, the creation of a recommendation model phase bears the highest load of the recommendation system, and it minimizes the load of the recommendation system in run-time. Therefore, the scalability problem and large scale recommendation system can be performed with collaborative filtering, which is highly reliable. Third, the missing user preference information is predicted using the item and user clusters. Using this method, the problem caused by the low density of the user preference matrix can be mitigated. Existing studies on this used an item-based prediction or user-based prediction. In this paper, Hao Ji's idea, which uses both an item-based prediction and user-based prediction, was improved. The reliability of the recommendation service can be improved by combining the predictive values of both techniques by applying the condition of the recommendation model. By predicting the user preference based on the item or user clusters, the time required to predict the user preference can be reduced, and missing user preference in run-time can be predicted. Fourth, the item and user feature vector can be made to learn the following input of the user feedback. This phase applied normalized user feedback to the item and user feature vector. This method can mitigate the problems caused by the use of the concepts of context-based filtering, such as the item and user feature vector based on the user profile and item properties. The problems with using the item and user feature vector are due to the limitation of quantifying the qualitative features of the items and users. Therefore, the elements of the user and item feature vectors are made to match one to one, and if user feedback to a particular item is obtained, it will be applied to the feature vector using the opposite one. Verification of this method was accomplished by comparing the performance with existing hybrid filtering techniques. Two methods were used for verification: MAE(Mean Absolute Error) and response time. Using MAE, this technique was confirmed to improve the reliability of the recommendation system. Using the response time, this technique was found to be suitable for a large scaled recommendation system. This paper suggested an Adaptive Clustering-based Collaborative Filtering Technique with high reliability and low time complexity, but it had some limitations. This technique focused on reducing the time complexity. Hence, an improvement in reliability was not expected. The next topic will be to improve this technique by rule-based filtering.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.57-71
• /
• 2013

Over a billion people in the world generate new news minute by minute. People forecasts some news but most news are from unexpected events such as natural disasters, accidents, crimes. People spend much time to watch a huge amount of news delivered from many media because they want to understand what is happening now, to predict what might happen in the near future, and to share and discuss on the news. People make better daily decisions through watching and obtaining useful information from news they saw. However, it is difficult that people choose news suitable to them and obtain useful information from the news because there are so many news media such as portal sites, broadcasters, and most news articles consist of gossipy news and breaking news. User interest changes over time and many people have no interest in outdated news. From this fact, applying users' recent interest to personalized news service is also required in news service. It means that personalized news service should dynamically manage user profiles. In this paper, a content-based news recommendation system is proposed to provide the personalized news service. For a personalized service, user's personal information is requisitely required. Social network service is used to extract user information for personalization service. The proposed system constructs dynamic user profile based on recent user information of Facebook, which is one of social network services. User information contains personal information, recent articles, and Facebook Page information. Facebook Pages are used for businesses, organizations and brands to share their contents and connect with people. Facebook users can add Facebook Page to specify their interest in the Page. The proposed system uses this Page information to create user profile, and to match user preferences to news topics. However, some Pages are not directly matched to news topic because Page deals with individual objects and do not provide topic information suitable to news. Freebase, which is a large collaborative database of well-known people, places, things, is used to match Page to news topic by using hierarchy information of its objects. By using recent Page information and articles of Facebook users, the proposed systems can own dynamic user profile. The generated user profile is used to measure user preferences on news. To generate news profile, news category predefined by news media is used and keywords of news articles are extracted after analysis of news contents including title, category, and scripts. TF-IDF technique, which reflects how important a word is to a document in a corpus, is used to identify keywords of each news article. For user profile and news profile, same format is used to efficiently measure similarity between user preferences and news. The proposed system calculates all similarity values between user profiles and news profiles. Existing methods of similarity calculation in vector space model do not cover synonym, hypernym and hyponym because they only handle given words in vector space model. The proposed system applies WordNet to similarity calculation to overcome the limitation. Top-N news articles, which have high similarity value for a target user, are recommended to the user. To evaluate the proposed news recommendation system, user profiles are generated using Facebook account with participants consent, and we implement a Web crawler to extract news information from PBS, which is non-profit public broadcasting television network in the United States, and construct news profiles. We compare the performance of the proposed method with that of benchmark algorithms. One is a traditional method based on TF-IDF. Another is 6Sub-Vectors method that divides the points to get keywords into six parts. Experimental results demonstrate that the proposed system provide useful news to users by applying user's social network information and WordNet functions, in terms of prediction error of recommended news.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.27-42
• /
• 2020

Traditional companies with offline stores were unable to secure large display space due to the problems of cost. This limitation inevitably allowed limited kinds of products to be displayed on the shelves, which resulted in consumers being deprived of the opportunity to experience various items. Taking advantage of the virtual space called the Internet, online shopping goes beyond the limits of limitations in physical space of offline shopping and is now able to display numerous products on web pages that can satisfy consumers with a variety of needs. Paradoxically, however, this can also cause consumers to experience the difficulty of comparing and evaluating too many alternatives in their purchase decision-making process. As an effort to address this side effect, various kinds of consumer's purchase decision support systems have been studied, such as keyword-based item search service and recommender systems. These systems can reduce search time for items, prevent consumer from leaving while browsing, and contribute to the seller's increased sales. Among those systems, recommender systems based on association rule mining techniques can effectively detect interrelated products from transaction data such as orders. The association between products obtained by statistical analysis provides clues to predicting how interested consumers will be in another product. However, since its algorithm is based on the number of transactions, products not sold enough so far in the early days of launch may not be included in the list of recommendations even though they are highly likely to be sold. Such missing items may not have sufficient opportunities to be exposed to consumers to record sufficient sales, and then fall into a vicious cycle of a vicious cycle of declining sales and omission in the recommendation list. This situation is an inevitable outcome in situations in which recommendations are made based on past transaction histories, rather than on determining potential future sales possibilities. This study started with the idea that reflecting the means by which this potential possibility can be identified indirectly would help to select highly recommended products. In the light of the fact that the attributes of a product affect the consumer's purchasing decisions, this study was conducted to reflect them in the recommender systems. In other words, consumers who visit a product page have shown interest in the attributes of the product and would be also interested in other products with the same attributes. On such assumption, based on these attributes, the recommender system can select recommended products that can show a higher acceptance rate. Given that a category is one of the main attributes of a product, it can be a good indicator of not only direct associations between two items but also potential associations that have yet to be revealed. Based on this idea, the study devised a recommender system that reflects not only associations between products but also categories. Through regression analysis, two kinds of associations were combined to form a model that could predict the hit rate of recommendation. To evaluate the performance of the proposed model, another regression model was also developed based only on associations between products. Comparative experiments were designed to be similar to the environment in which products are actually recommended in online shopping malls. First, the association rules for all possible combinations of antecedent and consequent items were generated from the order data. Then, hit rates for each of the associated rules were predicted from the support and confidence that are calculated by each of the models. The comparative experiments using order data collected from an online shopping mall show that the recommendation accuracy can be improved by further reflecting not only the association between products but also categories in the recommendation of related products. The proposed model showed a 2 to 3 percent improvement in hit rates compared to the existing model. From a practical point of view, it is expected to have a positive effect on improving consumers' purchasing satisfaction and increasing sellers' sales.