• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.23-46
• /
• 2021

Collaborative filtering, which is often used in personalization recommendations, is recognized as a very useful technique to find similar customers and recommend products to them based on their purchase history. However, the traditional collaborative filtering technique has raised the question of having difficulty calculating the similarity for new customers or products due to the method of calculating similaritiesbased on direct connections and common features among customers. For this reason, a hybrid technique was designed to use content-based filtering techniques together. On the one hand, efforts have been made to solve these problems by applying the structural characteristics of social networks. This applies a method of indirectly calculating similarities through their similar customers placed between them. This means creating a customer's network based on purchasing data and calculating the similarity between the two based on the features of the network that indirectly connects the two customers within this network. Such similarity can be used as a measure to predict whether the target customer accepts recommendations. The centrality metrics of networks can be utilized for the calculation of these similarities. Different centrality metrics have important implications in that they may have different effects on recommended performance. In this study, furthermore, the effect of these centrality metrics on the performance of recommendation may vary depending on recommender algorithms. In addition, recommendation techniques using network analysis can be expected to contribute to increasing recommendation performance even if they apply not only to new customers or products but also to entire customers or products. By considering a customer's purchase of an item as a link generated between the customer and the item on the network, the prediction of user acceptance of recommendation is solved as a prediction of whether a new link will be created between them. As the classification models fit the purpose of solving the binary problem of whether the link is engaged or not, decision tree, k-nearest neighbors (KNN), logistic regression, artificial neural network, and support vector machine (SVM) are selected in the research. The data for performance evaluation used order data collected from an online shopping mall over four years and two months. Among them, the previous three years and eight months constitute social networks composed of and the experiment was conducted by organizing the data collected into the social network. The next four months' records were used to train and evaluate recommender models. Experiments with the centrality metrics applied to each model show that the recommendation acceptance rates of the centrality metrics are different for each algorithm at a meaningful level. In this work, we analyzed only four commonly used centrality metrics: degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. Eigenvector centrality records the lowest performance in all models except support vector machines. Closeness centrality and betweenness centrality show similar performance across all models. Degree centrality ranking moderate across overall models while betweenness centrality always ranking higher than degree centrality. Finally, closeness centrality is characterized by distinct differences in performance according to the model. It ranks first in logistic regression, artificial neural network, and decision tree withnumerically high performance. However, it only records very low rankings in support vector machine and K-neighborhood with low-performance levels. As the experiment results reveal, in a classification model, network centrality metrics over a subnetwork that connects the two nodes can effectively predict the connectivity between two nodes in a social network. Furthermore, each metric has a different performance depending on the classification model type. This result implies that choosing appropriate metrics for each algorithm can lead to achieving higher recommendation performance. In general, betweenness centrality can guarantee a high level of performance in any model. It would be possible to consider the introduction of proximity centrality to obtain higher performance for certain models.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.83-102
• /
• 2021

The government recently announced various policies for developing big-data and artificial intelligence fields to provide a great opportunity to the public with respect to disclosure of high-quality data within public institutions. KSURE(Korea Trade Insurance Corporation) is a major public institution for financial policy in Korea, and thus the company is strongly committed to backing export companies with various systems. Nevertheless, there are still fewer cases of realized business model based on big-data analyses. In this situation, this paper aims to develop a new business model which can be applied to an ex-ante prediction for the likelihood of the insurance accident of credit guarantee. We utilize internal data from KSURE which supports export companies in Korea and apply machine learning models. Then, we conduct performance comparison among the predictive models including Logistic Regression, Random Forest, XGBoost, LightGBM, and DNN(Deep Neural Network). For decades, many researchers have tried to find better models which can help to predict bankruptcy since the ex-ante prediction is crucial for corporate managers, investors, creditors, and other stakeholders. The development of the prediction for financial distress or bankruptcy was originated from Smith(1930), Fitzpatrick(1932), or Merwin(1942). One of the most famous models is the Altman's Z-score model(Altman, 1968) which was based on the multiple discriminant analysis. This model is widely used in both research and practice by this time. The author suggests the score model that utilizes five key financial ratios to predict the probability of bankruptcy in the next two years. Ohlson(1980) introduces logit model to complement some limitations of previous models. Furthermore, Elmer and Borowski(1988) develop and examine a rule-based, automated system which conducts the financial analysis of savings and loans. Since the 1980s, researchers in Korea have started to examine analyses on the prediction of financial distress or bankruptcy. Kim(1987) analyzes financial ratios and develops the prediction model. Also, Han et al.(1995, 1996, 1997, 2003, 2005, 2006) construct the prediction model using various techniques including artificial neural network. Yang(1996) introduces multiple discriminant analysis and logit model. Besides, Kim and Kim(2001) utilize artificial neural network techniques for ex-ante prediction of insolvent enterprises. After that, many scholars have been trying to predict financial distress or bankruptcy more precisely based on diverse models such as Random Forest or SVM. One major distinction of our research from the previous research is that we focus on examining the predicted probability of default for each sample case, not only on investigating the classification accuracy of each model for the entire sample. Most predictive models in this paper show that the level of the accuracy of classification is about 70% based on the entire sample. To be specific, LightGBM model shows the highest accuracy of 71.1% and Logit model indicates the lowest accuracy of 69%. However, we confirm that there are open to multiple interpretations. In the context of the business, we have to put more emphasis on efforts to minimize type 2 error which causes more harmful operating losses for the guaranty company. Thus, we also compare the classification accuracy by splitting predicted probability of the default into ten equal intervals. When we examine the classification accuracy for each interval, Logit model has the highest accuracy of 100% for 0~10% of the predicted probability of the default, however, Logit model has a relatively lower accuracy of 61.5% for 90~100% of the predicted probability of the default. On the other hand, Random Forest, XGBoost, LightGBM, and DNN indicate more desirable results since they indicate a higher level of accuracy for both 0~10% and 90~100% of the predicted probability of the default but have a lower level of accuracy around 50% of the predicted probability of the default. When it comes to the distribution of samples for each predicted probability of the default, both LightGBM and XGBoost models have a relatively large number of samples for both 0~10% and 90~100% of the predicted probability of the default. Although Random Forest model has an advantage with regard to the perspective of classification accuracy with small number of cases, LightGBM or XGBoost could become a more desirable model since they classify large number of cases into the two extreme intervals of the predicted probability of the default, even allowing for their relatively low classification accuracy. Considering the importance of type 2 error and total prediction accuracy, XGBoost and DNN show superior performance. Next, Random Forest and LightGBM show good results, but logistic regression shows the worst performance. However, each predictive model has a comparative advantage in terms of various evaluation standards. For instance, Random Forest model shows almost 100% accuracy for samples which are expected to have a high level of the probability of default. Collectively, we can construct more comprehensive ensemble models which contain multiple classification machine learning models and conduct majority voting for maximizing its overall performance.

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.159-185
• /
• 2016

Planning a multi-day trip is a complex, yet time-consuming task. It usually starts with selecting a list of points of interest (POIs) worth visiting and then arranging them into an itinerary, taking into consideration various constraints and preferences. When choosing POIs to visit, one might ask friends to suggest them, search for information on the Web, or seek advice from travel agents; however, those options have their limitations. First, the knowledge of friends is limited to the places they have visited. Second, the tourism information on the internet may be vast, but at the same time, might cause one to invest a lot of time reading and filtering the information. Lastly, travel agents might be biased towards providers of certain travel products when suggesting itineraries. In recent years, many researchers have tried to deal with the huge amount of tourism information available on the internet. They explored the wisdom of the crowd through overwhelming images shared by people on social media sites. Furthermore, trip planning problems are usually formulated as 'Tourist Trip Design Problems', and are solved using various search algorithms with heuristics. Various recommendation systems with various techniques have been set up to cope with the overwhelming tourism information available on the internet. Prediction models of recommendation systems are typically built using a large dataset. However, sometimes such a dataset is not always available. For other models, especially those that require input from people, human computation has emerged as a powerful and inexpensive approach. This study proposes CYTRIP (Crowdsource Your TRIP), a multi-day trip itinerary planning system that draws on the collective intelligence of contributors in recommending POIs. In order to enable the crowd to collaboratively recommend POIs to users, CYTRIP provides a shared workspace. In the shared workspace, the crowd can recommend as many POIs to as many requesters as they can, and they can also vote on the POIs recommended by other people when they find them interesting. In CYTRIP, anyone can make a contribution by recommending POIs to requesters based on requesters' specified preferences. CYTRIP takes input on the recommended POIs to build a multi-day trip itinerary taking into account the user's preferences, the various time constraints, and the locations. The input then becomes a multi-day trip planning problem that is formulated in Planning Domain Definition Language 3 (PDDL3). A sequence of actions formulated in a domain file is used to achieve the goals in the planning problem, which are the recommended POIs to be visited. The multi-day trip planning problem is a highly constrained problem. Sometimes, it is not feasible to visit all the recommended POIs with the limited resources available, such as the time the user can spend. In order to cope with an unachievable goal that can result in no solution for the other goals, CYTRIP selects a set of feasible POIs prior to the planning process. The planning problem is created for the selected POIs and fed into the planner. The solution returned by the planner is then parsed into a multi-day trip itinerary and displayed to the user on a map. The proposed system is implemented as a web-based application built using PHP on a CodeIgniter Web Framework. In order to evaluate the proposed system, an online experiment was conducted. From the online experiment, results show that with the help of the contributors, CYTRIP can plan and generate a multi-day trip itinerary that is tailored to the users' preferences and bound by their constraints, such as location or time constraints. The contributors also find that CYTRIP is a useful tool for collecting POIs from the crowd and planning a multi-day trip.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.113-127
• /
• 2016

Among the techniques for recommendation, collaborative filtering (CF) is commonly recognized to be the most effective for implementing recommender systems. Until now, CF has been popularly studied and adopted in both academic and real-world applications. The basic idea of CF is to create recommendation results by finding correlations between users of a recommendation system. CF system compares users based on how similar they are, and recommend products to users by using other like-minded people's results of evaluation for each product. Thus, it is very important to compute evaluation similarities among users in CF because the recommendation quality depends on it. Typical CF uses user's explicit numeric ratings of items (i.e. quantitative information) when computing the similarities among users in CF. In other words, user's numeric ratings have been a sole source of user preference information in traditional CF. However, user ratings are unable to fully reflect user's actual preferences from time to time. According to several studies, users may more actively accommodate recommendation of reliable others when purchasing goods. Thus, trust relationship can be regarded as the informative source for identifying user's preference with accuracy. Under this background, we propose a new hybrid recommender system that fuses CF and social network analysis (SNA). The proposed system adopts the recommendation algorithm that additionally reflect the result analyzed by SNA. In detail, our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and trust relationship information between users when calculating user similarities. For this, our system creates and uses not only user-item rating matrix, but also user-to-user trust network. As the methods for calculating user similarity between users, we proposed two alternatives - one is algorithm calculating the degree of similarity between users by utilizing in-degree and out-degree centrality, which are the indices representing the central location in the social network. We named these approaches as 'Trust CF - All' and 'Trust CF - Conditional'. The other alternative is the algorithm reflecting a neighbor's score higher when a target user trusts the neighbor directly or indirectly. The direct or indirect trust relationship can be identified by searching trust network of users. In this study, we call this approach 'Trust CF - Search'. To validate the applicability of the proposed system, we used experimental data provided by LibRec that crawled from the entire FilmTrust website. It consists of ratings of movies and trust relationship network indicating who to trust between users. The experimental system was implemented using Microsoft Visual Basic for Applications (VBA) and UCINET 6. To examine the effectiveness of the proposed system, we compared the performance of our proposed method with one of conventional CF system. The performances of recommender system were evaluated by using average MAE (mean absolute error). The analysis results confirmed that in case of applying without conditions the in-degree centrality index of trusted network of users(i.e. Trust CF - All), the accuracy (MAE = 0.565134) was lower than conventional CF (MAE = 0.564966). And, in case of applying the in-degree centrality index only to the users with the out-degree centrality above a certain threshold value(i.e. Trust CF - Conditional), the proposed system improved the accuracy a little (MAE = 0.564909) compared to traditional CF. However, the algorithm searching based on the trusted network of users (i.e. Trust CF - Search) was found to show the best performance (MAE = 0.564846). And the result from paired samples t-test presented that Trust CF - Search outperformed conventional CF with 10% statistical significance level. Our study sheds a light on the application of user's trust relationship network information for facilitating electronic commerce by recommending proper items to users.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.71-89
• /
• 2016

Sentiment analysis is used for identifying emotions or sentiments embedded in the user generated data such as customer reviews from blogs, social network services, and so on. Various research fields such as computer science and business management can take advantage of this feature to analyze customer-generated opinions. In previous studies, the star rating of a review is regarded as the same as sentiment embedded in the text. However, it does not always correspond to the sentiment polarity. Due to this supposition, previous studies have some limitations in their accuracy. To solve this issue, the present study uses a supervised sentiment classification model to measure a more accurate sentiment polarity. This study aims to propose an advanced sentiment classifier and to discover the correlation between movie reviews and box-office success. The advanced sentiment classifier is based on two supervised machine learning techniques, the Support Vector Machines (SVM) and Feedforward Neural Network (FNN). The sentiment scores of the movie reviews are measured by the sentiment classifier and are analyzed by statistical correlations between movie reviews and box-office success. Movie reviews are collected along with a star-rate. The dataset used in this study consists of 1,258,538 reviews from 175 films gathered from Naver Movie website (movie.naver.com). The results show that the proposed sentiment classifier outperforms Naive Bayes (NB) classifier as its accuracy is about 6% higher than NB. Furthermore, the results indicate that there are positive correlations between the star-rate and the number of audiences, which can be regarded as the box-office success of a movie. The study also shows that there is the mild, positive correlation between the sentiment scores estimated by the classifier and the number of audiences. To verify the applicability of the sentiment scores, an independent sample t-test was conducted. For this, the movies were divided into two groups using the average of sentiment scores. The two groups are significantly different in terms of the star-rated scores.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.39-70
• /
• 2017

Data-drive analytics techniques have been recently applied to public surveys. Instead of simply gathering survey results or expert opinions to research the preference for a recently launched product, enterprises need a way to collect and analyze various types of online data and then accurately figure out customer preferences. In the main concept of existing data-based survey methods, the sentiment lexicon for a particular domain is first constructed by domain experts who usually judge the positive, neutral, or negative meanings of the frequently used words from the collected text documents. In order to research the preference for a particular product, the existing approach collects (1) review posts, which are related to the product, from several product review web sites; (2) extracts sentences (or phrases) in the collection after the pre-processing step such as stemming and removal of stop words is performed; (3) classifies the polarity (either positive or negative sense) of each sentence (or phrase) based on the sentiment lexicon; and (4) estimates the positive and negative ratios of the product by dividing the total numbers of the positive and negative sentences (or phrases) by the total number of the sentences (or phrases) in the collection. Furthermore, the existing approach automatically finds important sentences (or phrases) including the positive and negative meaning to/against the product. As a motivated example, given a product like Sonata made by Hyundai Motors, customers often want to see the summary note including what positive points are in the 'car design' aspect as well as what negative points are in thesame aspect. They also want to gain more useful information regarding other aspects such as 'car quality', 'car performance', and 'car service.' Such an information will enable customers to make good choice when they attempt to purchase brand-new vehicles. In addition, automobile makers will be able to figure out the preference and positive/negative points for new models on market. In the near future, the weak points of the models will be improved by the sentiment analysis. For this, the existing approach computes the sentiment score of each sentence (or phrase) and then selects top-k sentences (or phrases) with the highest positive and negative scores. However, the existing approach has several shortcomings and is limited to apply to real applications. The main disadvantages of the existing approach is as follows: (1) The main aspects (e.g., car design, quality, performance, and service) to a product (e.g., Hyundai Sonata) are not considered. Through the sentiment analysis without considering aspects, as a result, the summary note including the positive and negative ratios of the product and top-k sentences (or phrases) with the highest sentiment scores in the entire corpus is just reported to customers and car makers. This approach is not enough and main aspects of the target product need to be considered in the sentiment analysis. (2) In general, since the same word has different meanings across different domains, the sentiment lexicon which is proper to each domain needs to be constructed. The efficient way to construct the sentiment lexicon per domain is required because the sentiment lexicon construction is labor intensive and time consuming. To address the above problems, in this article, we propose a novel product reputation mining algorithm that (1) extracts topics hidden in review documents written by customers; (2) mines main aspects based on the extracted topics; (3) measures the positive and negative ratios of the product using the aspects; and (4) presents the digest in which a few important sentences with the positive and negative meanings are listed in each aspect. Unlike the existing approach, using hidden topics makes experts construct the sentimental lexicon easily and quickly. Furthermore, reinforcing topic semantics, we can improve the accuracy of the product reputation mining algorithms more largely than that of the existing approach. In the experiments, we collected large review documents to the domestic vehicles such as K5, SM5, and Avante; measured the positive and negative ratios of the three cars; showed top-k positive and negative summaries per aspect; and conducted statistical analysis. Our experimental results clearly show the effectiveness of the proposed method, compared with the existing method.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.143-159
• /
• 2017

Due to the rapid development of IT in recent years, not only personal information but also the key technologies and information leakage that companies have are becoming important issues. For the enterprise, the core technology that the company possesses is a very important part for the survival of the enterprise and for the continuous competitive advantage. Recently, there have been many cases of technical infringement. Technology leaks not only cause tremendous financial losses such as falling stock prices for companies, but they also have a negative impact on corporate reputation and delays in corporate development. In the case of SMEs, where core technology is an important part of the enterprise, compared to large corporations, the preparation for technological leakage can be seen as an indispensable factor in the existence of the enterprise. As the necessity and importance of Information Security Management (ISM) is emerging, it is necessary to check and prepare for the threat of technology infringement early in the enterprise. Nevertheless, previous studies have shown that the majority of policy alternatives are represented by about 90%. As a research method, literature analysis accounted for 76% and empirical and statistical analysis accounted for a relatively low rate of 16%. For this reason, it is necessary to study the management model and prediction model to prevent leakage of technology to meet the characteristics of SMEs. In this study, before analyzing the empirical analysis, we divided the technical characteristics from the technology value perspective and the organizational factor from the technology control point based on many previous researches related to the factors affecting the technology leakage. A total of 12 related variables were selected for the two factors, and the analysis was performed with these variables. In this study, we use three - year data of "Small and Medium Enterprise Technical Statistics Survey" conducted by the Small and Medium Business Administration. Analysis data includes 30 industries based on KSIC-based 2-digit classification, and the number of companies affected by technology leakage is 415 over 3 years. Through this data, we conducted a randomized sampling in the same industry based on the KSIC in the same year, and compared with the companies (n = 415) and the unaffected firms (n = 415) 1:1 Corresponding samples were prepared and analyzed. In this research, we will conduct an empirical analysis to search for factors influencing technology leakage, and propose an early warning system through data mining. Specifically, in this study, based on the questionnaire survey of SMEs conducted by the Small and Medium Business Administration (SME), we classified the factors that affect the technology leakage of SMEs into two factors(Technology Characteristics, Organization Characteristics). And we propose a model that informs the possibility of technical infringement by using Support Vector Machine(SVM) which is one of the various techniques of data mining based on the proven factors through statistical analysis. Unlike previous studies, this study focused on the cases of various industries in many years, and it can be pointed out that the artificial intelligence model was developed through this study. In addition, since the factors are derived empirically according to the actual leakage of SME technology leakage, it will be possible to suggest to policy makers which companies should be managed from the viewpoint of technology protection. Finally, it is expected that the early warning model on the possibility of technology leakage proposed in this study will provide an opportunity to prevent technology Leakage from the viewpoint of enterprise and government in advance.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.111-125
• /
• 2011

Clustering is a process of grouping similar or relevant documents into a cluster and assigning a meaningful concept to the cluster. By this process, clustering facilitates fast and correct search for the relevant documents by narrowing down the range of searching only to the collection of documents belonging to related clusters. For effective clustering, techniques are required for identifying similar documents and grouping them into a cluster, and discovering a concept that is most relevant to the cluster. One of the problems often appearing in this context is the detection of a complex concept that overlaps with several simple concepts at the same hierarchical level. Previous clustering methods were unable to identify and represent a complex concept that belongs to several different clusters at the same level in the concept hierarchy, and also could not validate the semantic hierarchical relationship between a complex concept and each of simple concepts. In order to solve these problems, this paper proposes a new clustering method that identifies and represents complex concepts efficiently. We developed the Hierarchical Overlapping Clustering (HOC) algorithm that modified the traditional Agglomerative Hierarchical Clustering algorithm to allow overlapped clusters at the same level in the concept hierarchy. The HOC algorithm represents the clustering result not by a tree but by a lattice to detect complex concepts. We developed a system that employs the HOC algorithm to carry out the goal of complex concept detection. This system operates in three phases; 1) the preprocessing of documents, 2) the clustering using the HOC algorithm, and 3) the validation of semantic hierarchical relationships among the concepts in the lattice obtained as a result of clustering. The preprocessing phase represents the documents as x-y coordinate values in a 2-dimensional space by considering the weights of terms appearing in the documents. First, it goes through some refinement process by applying stopwords removal and stemming to extract index terms. Then, each index term is assigned a TF-IDF weight value and the x-y coordinate value for each document is determined by combining the TF-IDF values of the terms in it. The clustering phase uses the HOC algorithm in which the similarity between the documents is calculated by applying the Euclidean distance method. Initially, a cluster is generated for each document by grouping those documents that are closest to it. Then, the distance between any two clusters is measured, grouping the closest clusters as a new cluster. This process is repeated until the root cluster is generated. In the validation phase, the feature selection method is applied to validate the appropriateness of the cluster concepts built by the HOC algorithm to see if they have meaningful hierarchical relationships. Feature selection is a method of extracting key features from a document by identifying and assigning weight values to important and representative terms in the document. In order to correctly select key features, a method is needed to determine how each term contributes to the class of the document. Among several methods achieving this goal, this paper adopted the $x^2$�� statistics, which measures the dependency degree of a term t to a class c, and represents the relationship between t and c by a numerical value. To demonstrate the effectiveness of the HOC algorithm, a series of performance evaluation is carried out by using a well-known Reuter-21578 news collection. The result of performance evaluation showed that the HOC algorithm greatly contributes to detecting and producing complex concepts by generating the concept hierarchy in a lattice structure.

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

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

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.121-139
• /
• 2014

Predicting corporate failure has been an important topic in accounting and finance. The costs associated with bankruptcy are high, so the accuracy of bankruptcy prediction is greatly important for financial institutions. Lots of researchers have dealt with the topic associated with bankruptcy prediction in the past three decades. The current research attempts to use ensemble models for improving the performance of bankruptcy prediction. Ensemble classification is to combine individually trained classifiers in order to gain more accurate prediction than individual models. Ensemble techniques are shown to be very useful for improving the generalization ability of the classifier. Bagging is the most commonly used methods for constructing ensemble classifiers. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. Instance selection is to select critical instances while deleting and removing irrelevant and harmful instances from the original set. Instance selection and bagging are quite well known in data mining. However, few studies have dealt with the integration of instance selection and bagging. This study proposes an improved bagging ensemble based on instance selection using genetic algorithms (GA) for improving the performance of SVM. GA is an efficient optimization procedure based on the theory of natural selection and evolution. GA uses the idea of survival of the fittest by progressively accepting better solutions to the problems. GA searches by maintaining a population of solutions from which better solutions are created rather than making incremental changes to a single solution to the problem. The initial solution population is generated randomly and evolves into the next generation by genetic operators such as selection, crossover and mutation. The solutions coded by strings are evaluated by the fitness function. The proposed model consists of two phases: GA based Instance Selection and Instance based Bagging. In the first phase, GA is used to select optimal instance subset that is used as input data of bagging model. In this study, the chromosome is encoded as a form of binary string for the instance subset. In this phase, the population size was set to 100 while maximum number of generations was set to 150. We set the crossover rate and mutation rate to 0.7 and 0.1 respectively. We used the prediction accuracy of model as the fitness function of GA. SVM model is trained on training data set using the selected instance subset. The prediction accuracy of SVM model over test data set is used as fitness value in order to avoid overfitting. In the second phase, we used the optimal instance subset selected in the first phase as input data of bagging model. We used SVM model as base classifier for bagging ensemble. The majority voting scheme was used as a combining method in this study. This study applies the proposed model to the bankruptcy prediction problem using a real data set from Korean companies. The research data used in this study contains 1832 externally non-audited firms which filed for bankruptcy (916 cases) and non-bankruptcy (916 cases). Financial ratios categorized as stability, profitability, growth, activity and cash flow were investigated through literature review and basic statistical methods and we selected 8 financial ratios as the final input variables. We separated the whole data into three subsets as training, test and validation data set. In this study, we compared the proposed model with several comparative models including the simple individual SVM model, the simple bagging model and the instance selection based SVM model. The McNemar tests were used to examine whether the proposed model significantly outperforms the other models. The experimental results show that the proposed model outperforms the other models.