• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.69-88
• /
• 2022

One of the characteristics of South Korea's economic structure is that it is highly dependent on exports. Thus, many businesses are closely related to the global economy and diplomatic situation. In addition, small and medium-sized enterprises(SMEs) specialized in exporting are struggling due to the spread of COVID-19. Therefore, this study aimed to develop a model to forecast exports for next year to support SMEs' export strategy and decision making. Also, this study proposed a strategy to recommend promising export countries of each item based on the forecasting model. We analyzed important variables used in previous studies such as country-specific, item-specific, and macro-economic variables and collected those variables to train our prediction model. Next, through the exploratory data analysis(EDA) it was found that exports, which is a target variable, have a highly skewed distribution. To deal with this issue and improve predictive performance, we suggest a separated learning method. In a separated learning method, the whole dataset is divided into homogeneous subgroups and a prediction algorithm is applied to each group. Thus, characteristics of each group can be more precisely trained using different input variables and algorithms. In this study, we divided the dataset into five subgroups based on the exports to decrease skewness of the target variable. After the separation, we found that each group has different characteristics in countries and goods. For example, In Group 1, most of the exporting countries are developing countries and the majority of exporting goods are low value products such as glass and prints. On the other hand, major exporting countries of South Korea such as China, USA, and Vietnam are included in Group 4 and Group 5 and most exporting goods in these groups are high value products. Then we used LightGBM(LGBM) and Exponential Moving Average(EMA) for prediction. Considering the characteristics of each group, models were built using LGBM for Group 1 to 4 and EMA for Group 5. To evaluate the performance of the model, we compare different model structures and algorithms. As a result, it was found that the separated learning model had best performance compared to other models. After the model was built, we also provided variable importance of each group using SHAP-value to add explainability of our model. Based on the prediction model, we proposed a second-stage recommendation strategy for potential export countries. In the first phase, BCG matrix was used to find Star and Question Mark markets that are expected to grow rapidly. In the second phase, we calculated scores for each country and recommendations were made according to ranking. Using this recommendation framework, potential export countries were selected and information about those countries for each item was presented. There are several implications of this study. First of all, most of the preceding studies have conducted research on the specific situation or country. However, this study use various variables and develops a machine learning model for a wide range of countries and items. Second, as to our knowledge, it is the first attempt to adopt a separated learning method for exports prediction. By separating the dataset into 5 homogeneous subgroups, we could enhance the predictive performance of the model. Also, more detailed explanation of models by group is provided using SHAP values. Lastly, this study has several practical implications. There are some platforms which serve trade information including KOTRA, but most of them are based on past data. Therefore, it is not easy for companies to predict future trends. By utilizing the model and recommendation strategy in this research, trade related services in each platform can be improved so that companies including SMEs can fully utilize the service when making strategies and decisions for exports.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.1-20
• /
• 2013

Nowadays, social network is a huge communication platform for providing people to connect with one another and to bring users together to share common interests, experiences, and their daily activities. Users spend hours per day in maintaining personal information and interacting with other people via posting, commenting, messaging, games, social events, and applications. Due to the growth of user's distributed information in social network, there is a great potential to utilize the social data to enhance the quality of recommender system. There are some researches focusing on social network analysis that investigate how social network can be used in recommendation domain. Among these researches, we are interested in taking advantages of the interaction between a user and others in social network that can be determined and known as social relationship. Furthermore, mostly user's decisions before purchasing some products depend on suggestion of people who have either the same preferences or closer relationship. For this reason, we believe that user's relationship in social network can provide an effective way to increase the quality in prediction user's interests of recommender system. Therefore, social relationship between users encountered from social network is a common factor to improve the way of predicting user's preferences in the conventional approach. Recommender system is dramatically increasing in popularity and currently being used by many e-commerce sites such as Amazon.com, Last.fm, eBay.com, etc. Collaborative filtering (CF) method is one of the essential and powerful techniques in recommender system for suggesting the appropriate items to user by learning user's preferences. CF method focuses on user data and generates automatic prediction about user's interests by gathering information from users who share similar background and preferences. Specifically, the intension of CF method is to find users who have similar preferences and to suggest target user items that were mostly preferred by those nearest neighbor users. There are two basic units that need to be considered by CF method, the user and the item. Each user needs to provide his rating value on items i.e. movies, products, books, etc to indicate their interests on those items. In addition, CF uses the user-rating matrix to find a group of users who have similar rating with target user. Then, it predicts unknown rating value for items that target user has not rated. Currently, CF has been successfully implemented in both information filtering and e-commerce applications. However, it remains some important challenges such as cold start, data sparsity, and scalability reflected on quality and accuracy of prediction. In order to overcome these challenges, many researchers have proposed various kinds of CF method such as hybrid CF, trust-based CF, social network-based CF, etc. In the purpose of improving the recommendation performance and prediction accuracy of standard CF, in this paper we propose a method which integrates traditional CF technique with social relationship between users discovered from user's behavior in social network i.e. Facebook. We identify user's relationship from behavior of user such as posts and comments interacted with friends in Facebook. We believe that social relationship implicitly inferred from user's behavior can be likely applied to compensate the limitation of conventional approach. Therefore, we extract posts and comments of each user by using Facebook Graph API and calculate feature score among each term to obtain feature vector for computing similarity of user. Then, we combine the result with similarity value computed using traditional CF technique. Finally, our system provides a list of recommended items according to neighbor users who have the biggest total similarity value to the target user. In order to verify and evaluate our proposed method we have performed an experiment on data collected from our Movies Rating System. Prediction accuracy evaluation is conducted to demonstrate how much our algorithm gives the correctness of recommendation to user in terms of MAE. Then, the evaluation of performance is made to show the effectiveness of our method in terms of precision, recall, and F1-measure. Evaluation on coverage is also included in our experiment to see the ability of generating recommendation. The experimental results show that our proposed method outperform and more accurate in suggesting items to users with better performance. The effectiveness of user's behavior in social network particularly shows the significant improvement by up to 6% on recommendation accuracy. Moreover, experiment of recommendation performance shows that incorporating social relationship observed from user's behavior into CF is beneficial and useful to generate recommendation with 7% improvement of performance compared with benchmark methods. Finally, we confirm that interaction between users in social network is able to enhance the accuracy and give better recommendation in conventional approach.

• Journal of KIISE:Databases
• /
• v.37 no.6
• /
• pp.343-350
• /
• 2010

We can get answers we want to know via questioning in Knowledge Search Service (KSS) based on Q&A Community. However, it is getting more difficult to find credible documents in enormous documents, since many anonymous users regardless of credibility are participate in answering on the question. In previous works in KSS, researchers evaluated the quality of documents based on textual information, e.g. recommendation count, click count and non-textual information, e.g. answer length, attached data, conjunction count. Then, the evaluation results are used for enhancing search performance. However, the non-textual information has a problem that it is difficult to get enough information by users in the early stage of Q&A. The textual information also has a limitation for evaluating quality because of judgement by partial factors such as answer length, conjunction counts. In this paper, we propose the QualityRank algorithm to improve the problem by textual and non-textual information. This algorithm ranks the relevant and credible answers by considering textual/non-textual information and user centrality based on Social Network Analysis(SNA). Based on experimental validation we can confirm that the results by our algorithm is improved than those of textual/non-textual in terms of ranking performance.

• Mood & Emotion
• /
• v.16 no.3
• /
• pp.123-128
• /
• 2018

Objectives : The fourth revision of Korean Medication Algorithm Project for Bipolar Disorder (KMAP-BP) was performed to provide more proper guidelines for clinicians. In this study, we evaluated treatment strategies of elderly patients with bipolar disorders of KMAP-BP 2018. Methods : Sixty-one psychiatrists of the review committee with vast clinical experiences in treating bipolar disorders, completed the survey. An expert consensus was obtained, on pharmacological treatment strategies for elderly patients with bipolar disorder. The executive committee analyzed results, and discussed the results to produce the final algorithm. Results : In elderly patients with bipolar disorder, first-line treatment option for acute manic episode is monotherapy, with atypical antipsychotics or mood stabilizer, and a combination of mood stabilizer and atypical antipsychotics. First-line treatment option for acute depressive episode, was a combination of mood stabilizer and atypical antipsychotics, monotherapy with atypical antipsychotic or mood stabilizer, and atypical antipsychotics with lamotrigine. Conclusion : In KMAP-BP 2018, the recommendation for treatment option in elderly patients with bipolar disorder, was newly introduced. We expect this algorithm may provide valuable information, and facilitate treatment of elderly patients with bipolar disorder.

• Journal of KIISE:Databases
• /
• v.37 no.2
• /
• pp.92-103
• /
• 2010

The Web Ontology Language (OWL) has become the W3C recommendation for publishing and sharing ontologies on the Semantic Web. To derive hidden information from OWL data, a number of OWL reasoners have been proposed. Since OWL reasoners are memory-based, they cannot handle large-sized OWL data. To overcome the scalability problem, RDBMS-based systems have been proposed. These systems store OWL data into a database and perform reasoning by incorporating the use of a database. However, they do not consider complete reasoning on all types of properties defined in OWL and the database schemas they use are ineffective for reasoning. In addition, they do not manage updates to the OWL data which can occur frequently in real applications. In this paper, we compare various database schemas used by RDBMS-based systems and propose an improved schema for efficient reasoning. Also, to support reasoning for all the types of properties defined in OWL, we propose a complete and efficient reasoning algorithm. Furthermore, we suggest efficient approaches to managing the updates that may occur on OWL data. Experimental results show that our schema has improved performance in OWL data storage and reasoning, and that our approaches to managing updates to OWL data are more efficient than the existing approaches.

• Knowledge Management Research
• /
• v.21 no.3
• /
• pp.27-44
• /
• 2020

In order to solve the user's information overload problem, recommender systems infer users' preferences and suggest items that match them. The collaborative filtering (CF), the most successful recommendation algorithm, has been improving performance until recently and applied to various business domains. Visual information, such as book covers, could influence consumers' purchase decision making. However, CF-based recommender systems have rarely considered for visual information. In this study, we propose VizNCS, a CF-based deep learning model that uses visual information as additional information. VizNCS consists of two phases. In the first phase, we build convolutional neural networks (CNN) to extract visual features from image data. In the second phase, we supply the visual features to the NCF model that is known to easy to extend to other information among the deep learning-based recommendation systems. As the results of the performance comparison experiments, VizNCS showed higher performance than the vanilla NCF. We also conducted an additional experiment to see if the visual information affects differently depending on the product category. The result enables us to identify which categories were affected and which were not. We expect VizNCS to improve the recommender system performance and expand the recommender system's data source to visual information.

• Journal of Broadcast Engineering
• /
• v.17 no.1
• /
• pp.129-139
• /
• 2012

This paper introduces a recommender system that is to recommend broadcast content. Our recommender system uses user's viewing history for personalized recommendations. Broadcast contents has unique characteristics as compared with books, musics and movies. There are two types of broadcast content, a series program and an episode program. The series program is comprised of several programs that deal with the same topic or story. Meanwhile, the episode program covers a variety of topics. Each program of those has different topic in general. Therefore, our recommender system recommends TV programs to users according to the type of broadcast content. The recommendations in this system are based on user's viewing history that is used to calculate content similarity between contents. Content similarity is calculated by exploiting collaborative filtering algorithm. Our recommender system uses java sparse array structure and performs memory-based processing. And then the results of processing are stored as an index structure. Our recommender system provides recommendation items through OPEN APIs that utilize the HTTP Protocol. Finally, this paper introduces the implementation of our recommender system and our web demo.

• Information Systems Review
• /
• v.22 no.4
• /
• pp.75-92
• /
• 2020

As population and generation structures change, more and more customers tend to avoid facing relation due to the development of information technology and spread of smart phones. This phenomenon consists with efficiency and immediacy, which are the consumption patterns of modern customers who are used to information technology, so offline network-oriented distribution companies actively try to switch their sales and services to untact patterns. Recently, untact services are boosted in various fields, but beauty products are not easy to be recommended through untact services due to many options depending on skin types and conditions. There have been many studies on recommendations and development of recommendation systems in the online beauty field, but most of them are the ones that develop recommendation algorithm using survey or social data. In other words, there were not enough studies that classify segments based on user information such as skin types and product preference. Therefore, this study classifies customer segments using machine learning technique K-prototypesalgorithm based on customer information and search log data of mobile application, which is one of untact services in the beauty field, based on which, untact marketing strategy is suggested. This study expands the scope of the previous literature by classifying customer segments using the machine learning technique. This study is practically meaningful in that it classifies customer segments by reflecting new consumption trend of untact service, and based on this, it suggests a specific plan that can be used in untact services of the beauty field.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.

• Journal of Broadcast Engineering
• /
• v.9 no.4 s.25
• /
• pp.305-321
• /
• 2004

With the advent of the digital broadcasting, the audiences can access a large number of TV programs and their information through the multiple channels on various media devices. The access to a large number of TV programs can support a user for many chances with which he/she can sort and select the best one of them. However, the information overload on the user inevitably requires much effort with a lot of patience for finding his/her favorite programs. Therefore, it is useful to provide the persona1ized broadcasting service which assists the user to automatically find his/her favorite programs. As the growing requirements of the TV personalization, we introduce our automatic user preference learning algorithm which 1) analyzes a user's usage history on TV program contents: 2) extracts the user's watching pattern depending on a specific time and day and shows our automatic TV program recommendation system using MPEG-7 MDS (Multimedia Description Scheme: ISO/IEC 15938-5) and 3) automatically calculates the user's preference. For our experimental results, we have used TV audiences' watching history with the ages, genders and viewing times obtained from AC Nielson Korea. From our experimental results, we observed that our proposed algorithm of the automatic user preference learning algorithm based on the Bayesian network can effectively learn the user's preferences accordingly during the course of TV watching periods.