• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.239-251
• /
• 2019

Statistical methods such as moving averages, Kalman filtering, exponential smoothing, regression analysis, and ARIMA (autoregressive integrated moving average) have been used for stock market predictions. However, these statistical methods have not produced superior performances. In recent years, machine learning techniques have been widely used in stock market predictions, including artificial neural network, SVM, and genetic algorithm. In particular, a case-based reasoning method, known as k-nearest neighbor is also widely used for stock price prediction. Case based reasoning retrieves several similar cases from previous cases when a new problem occurs, and combines the class labels of similar cases to create a classification for the new problem. However, case based reasoning has some problems. First, case based reasoning has a tendency to search for a fixed number of neighbors in the observation space and always selects the same number of neighbors rather than the best similar neighbors for the target case. So, case based reasoning may have to take into account more cases even when there are fewer cases applicable depending on the subject. Second, case based reasoning may select neighbors that are far away from the target case. Thus, case based reasoning does not guarantee an optimal pseudo-neighborhood for various target cases, and the predictability can be degraded due to a deviation from the desired similar neighbor. This paper examines how the size of learning data affects stock price predictability through k-nearest neighbor and compares the predictability of k-nearest neighbor with the random walk model according to the size of the learning data and the number of neighbors. In this study, Samsung electronics stock prices were predicted by dividing the learning dataset into two types. For the prediction of next day's closing price, we used four variables: opening value, daily high, daily low, and daily close. In the first experiment, data from January 1, 2000 to December 31, 2017 were used for the learning process. In the second experiment, data from January 1, 2015 to December 31, 2017 were used for the learning process. The test data is from January 1, 2018 to August 31, 2018 for both experiments. We compared the performance of k-NN with the random walk model using the two learning dataset. The mean absolute percentage error (MAPE) was 1.3497 for the random walk model and 1.3570 for the k-NN for the first experiment when the learning data was small. However, the mean absolute percentage error (MAPE) for the random walk model was 1.3497 and the k-NN was 1.2928 for the second experiment when the learning data was large. These results show that the prediction power when more learning data are used is higher than when less learning data are used. Also, this paper shows that k-NN generally produces a better predictive power than random walk model for larger learning datasets and does not when the learning dataset is relatively small. Future studies need to consider macroeconomic variables related to stock price forecasting including opening price, low price, high price, and closing price. Also, to produce better results, it is recommended that the k-nearest neighbor needs to find nearest neighbors using the second step filtering method considering fundamental economic variables as well as a sufficient amount of learning data.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.925-938
• /
• 2022

Agricultural reservoirs are an important water resource nationwide and vulnerable to abnormal climate effects such as drought caused by climate change. Therefore, it is required enhanced management for appropriate operation. Although water-level tracking is necessary through continuous monitoring, it is challenging to measure and observe on-site due to practical problems. This study presents an objective comparison between multiple AI models for water-body extraction using radar images that have the advantages of wide coverage, and frequent revisit time. The proposed methods in this study used Sentinel-1 Synthetic Aperture Radar (SAR) images, and unlike common methods of water extraction based on optical images, they are suitable for long-term monitoring because they are less affected by the weather conditions. We built four AI models such as Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), and Automated Machine Learning (AutoML) using drone images, sentinel-1 SAR and DSM data. There are total of 22 reservoirs of less than 1 million tons for the study, including small and medium-sized reservoirs with an effective storage capacity of less than 300,000 tons. 45 images from 22 reservoirs were used for model training and verification, and the results show that the AutoML model was 0.01 to 0.03 better in the water Intersection over Union (IoU) than the other three models, with Accuracy=0.92 and mIoU=0.81 in a test. As the result, AutoML performed as well as the classical machine learning methods and it is expected that the applicability of the water-body extraction technique by AutoML to monitor reservoirs automatically.

• Journal of the Society of Disaster Information
• /
• v.17 no.4
• /
• pp.864-881
• /
• 2021

Purpose: This study aims is to provide a total care solution preventing disaster based on Big Data and AI technology and to service safety considered by individual situations and various risk characteristics. The purpose is to suggest a method that customized comprehensive index services to prevent and respond to safety accidents for calculating the living safety index that quantitatively represent individual safety levels in relation to daily life safety. Method: In this study, we use method of mixing AHP(Analysis Hierarchy Process) and Likert Scale that extracted from consensus formation model of the expert group. We organize evaluation items that can evaluate life safety prevention services into risk indicators, vulnerability indicators, and prevention indicators. And We made up AHP hierarchical structure according to the AHP decision methodology and proposed a method to calculate relative weights between evaluation criteria through pairwise comparison of each level item. In addition, in consideration of the expansion of life safety prevention services in the future, the Likert scale is used instead of the AHP pair comparison and the weights between individual services are calculated. Result: We obtain result that is weights for life safety prevention services and reflected them in the individual risk index calculated through the artificial intelligence prediction model of life safety prevention services, so the comprehensive index was calculated. Conclusion: In order to apply the implemented model, a test environment consisting of a life safety prevention service app and platform was built, and the efficacy of the function was evaluated based on the user scenario. Through this, the life safety index presented in this study was confirmed to support the golden time for diagnosis, response and prevention of safety risks by comprehensively indication the user's current safety level.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.165-183
• /
• 2016

Over the past decade, there has been a rapid diffusion of technological devices and a rising number of various devices, resulting in an escalation of virtual reality technology. Technological market has rapidly been changed from smartphone to wearable devices based on virtual reality. Virtual reality can make users feel real situation through sensing interaction, voice, motion capture and so on. Facebook.com, Google, Samsung, LG, Sony and so on have investigated developing platform of virtual reality. the pricing of virtual reality devices also had decreased into 30% from their launched period. Thus market infrastructure in virtual reality have rapidly been developed to crease marketplace. However, most consumers recognize that virtual reality is not ease to purchase or use. That could not lead consumers to positive attitude for devices and purchase the related devices in the early market. Through previous studies related to virtual reality, there are few studies focusing on why the devices for virtual reality stayed in early stage in adoption & diffusion context in the market. Almost previous studies considered the reasons of hard adoption for innovative products in the viewpoints of Typology of Innovation Resistance, MIR(Management of Innovation Resistant), UTAUT & UTAUT2. However, product-based antecedents also important to increase user intention to purchase and use products in the technological market. In this study, we focus on user acceptance and resistance for increasing purchase and usage promotions of wearable devices related to virtual reality based on headgear products like Galaxy Gear. Especially, we added a variables like attitude confidence as a dimension for user resistance. The research questions of this study are follows. First, how attitude confidence and innovativeness resistance affect user intention to use? Second, What factors related to content and brand contexts can affect user intention to use? This research collected data from the participants who have experiences using virtual rality headgears aged between 20s to 50s located in South Korea. In order to collect data, this study used a pilot test and through making face-to-face interviews on three specialists, face validity and content validity were evaluated for the questionnaire validity. Cleansing the data, we dropped some outliers and data of irrelevant papers. Totally, 156 responses were used for testing the suggested hypotheses. Through collecting data, demographics and the relationships among variables were analyzed through conducting structural equation modeling by PLS. The data showed that the sex of respondents who have experience using social commerce sites (male=86(55.1%), female=70(44.9%). The ages of respondents are mostly from 20s (74.4%) to 30s (16.7%). 126 respondents (80.8%) have used virtual reality devices. The results of our model estimation are as follows. With the exception of Hypothesis 1 and 7, which deals with the two relationships between brand awareness to attitude confidence, and quality of content to perceived enjoyment, all of our hypotheses were supported. In compliance with our hypotheses, perceived ease of use (H2) and use innovativeness (H3) were supported with its positively influence for the attitude confidence. This finding indicates that the more ease of use and innovativeness for devices increased, the more users' attitude confidence increased. Perceived price (H4), enjoyment (H5), Quantity of contents (H6) significantly increase user resistance. However, perceived price positively affect user innovativeness resistance meanwhile perceived enjoyment and quantity of contents negatively affect user innovativeness resistance. In addition, aesthetic exterior (H6) was also positively associated with perceived price (p<0.01). Also projection quality (H8) can increase perceived enjoyment (p<0.05). Finally, attitude confidence (H10) increased user intention to use virtual reality devices. however user resistance (H11) negatively affect user intention to use virtual reality devices. The findings of this study show that attitude confidence and user innovativeness resistance differently influence customer intention for using virtual reality devices. There are two distinct characteristic of attitude confidence: perceived ease of use and user innovativeness. This study identified the antecedents of different roles of perceived price (aesthetic exterior) and perceived enjoyment (quality of contents & projection quality). The findings indicated that brand awareness and quality of contents for virtual reality is not formed within virtual reality market yet. Therefore, firms should developed brand awareness for their product in the virtual market to increase market share.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.123-138
• /
• 2017

Since the stock market is driven by the expectation of traders, studies have been conducted to predict stock price movements through analysis of various sources of text data. In order to predict stock price movements, research has been conducted not only on the relationship between text data and fluctuations in stock prices, but also on the trading stocks based on news articles and social media responses. Studies that predict the movements of stock prices have also applied classification algorithms with constructing term-document matrix in the same way as other text mining approaches. Because the document contains a lot of words, it is better to select words that contribute more for building a term-document matrix. Based on the frequency of words, words that show too little frequency or importance are removed. It also selects words according to their contribution by measuring the degree to which a word contributes to correctly classifying a document. The basic idea of constructing a term-document matrix was to collect all the documents to be analyzed and to select and use the words that have an influence on the classification. In this study, we analyze the documents for each individual item and select the words that are irrelevant for all categories as neutral words. We extract the words around the selected neutral word and use it to generate the term-document matrix. The neutral word itself starts with the idea that the stock movement is less related to the existence of the neutral words, and that the surrounding words of the neutral word are more likely to affect the stock price movements. And apply it to the algorithm that classifies the stock price fluctuations with the generated term-document matrix. In this study, we firstly removed stop words and selected neutral words for each stock. And we used a method to exclude words that are included in news articles for other stocks among the selected words. Through the online news portal, we collected four months of news articles on the top 10 market cap stocks. We split the news articles into 3 month news data as training data and apply the remaining one month news articles to the model to predict the stock price movements of the next day. We used SVM, Boosting and Random Forest for building models and predicting the movements of stock prices. The stock market opened for four months (2016/02/01 ~ 2016/05/31) for a total of 80 days, using the initial 60 days as a training set and the remaining 20 days as a test set. The proposed word - based algorithm in this study showed better classification performance than the word selection method based on sparsity. This study predicted stock price volatility by collecting and analyzing news articles of the top 10 stocks in market cap. We used the term - document matrix based classification model to estimate the stock price fluctuations and compared the performance of the existing sparse - based word extraction method and the suggested method of removing words from the term - document matrix. The suggested method differs from the word extraction method in that it uses not only the news articles for the corresponding stock but also other news items to determine the words to extract. In other words, it removed not only the words that appeared in all the increase and decrease but also the words that appeared common in the news for other stocks. When the prediction accuracy was compared, the suggested method showed higher accuracy. The limitation of this study is that the stock price prediction was set up to classify the rise and fall, and the experiment was conducted only for the top ten stocks. The 10 stocks used in the experiment do not represent the entire stock market. In addition, it is difficult to show the investment performance because stock price fluctuation and profit rate may be different. Therefore, it is necessary to study the research using more stocks and the yield prediction through trading simulation.

• Journal of Intelligence and Information Systems
• /
• v.21 no.4
• /
• pp.111-131
• /
• 2015

There are only a handful number of research conducted on pattern analysis of corporate distress as compared with research for bankruptcy prediction. The few that exists mainly focus on audited firms because financial data collection is easier for these firms. But in reality, corporate financial distress is a far more common and critical phenomenon for non-audited firms which are mainly comprised of small and medium sized firms. The purpose of this paper is to classify non-audited firms under distress according to their financial ratio using data mining; Self-Organizing Map (SOM). SOM is a type of artificial neural network that is trained using unsupervised learning to produce a lower dimensional discretized representation of the input space of the training samples, called a map. SOM is different from other artificial neural networks as it applies competitive learning as opposed to error-correction learning such as backpropagation with gradient descent, and in the sense that it uses a neighborhood function to preserve the topological properties of the input space. It is one of the popular and successful clustering algorithm. In this study, we classify types of financial distress firms, specially, non-audited firms. In the empirical test, we collect 10 financial ratios of 100 non-audited firms under distress in 2004 for the previous two years (2002 and 2003). Using these financial ratios and the SOM algorithm, five distinct patterns were distinguished. In pattern 1, financial distress was very serious in almost all financial ratios. 12% of the firms are included in these patterns. In pattern 2, financial distress was weak in almost financial ratios. 14% of the firms are included in pattern 2. In pattern 3, growth ratio was the worst among all patterns. It is speculated that the firms of this pattern may be under distress due to severe competition in their industries. Approximately 30% of the firms fell into this group. In pattern 4, the growth ratio was higher than any other pattern but the cash ratio and profitability ratio were not at the level of the growth ratio. It is concluded that the firms of this pattern were under distress in pursuit of expanding their business. About 25% of the firms were in this pattern. Last, pattern 5 encompassed very solvent firms. Perhaps firms of this pattern were distressed due to a bad short-term strategic decision or due to problems with the enterpriser of the firms. Approximately 18% of the firms were under this pattern. This study has the academic and empirical contribution. In the perspectives of the academic contribution, non-audited companies that tend to be easily bankrupt and have the unstructured or easily manipulated financial data are classified by the data mining technology (Self-Organizing Map) rather than big sized audited firms that have the well prepared and reliable financial data. In the perspectives of the empirical one, even though the financial data of the non-audited firms are conducted to analyze, it is useful for find out the first order symptom of financial distress, which makes us to forecast the prediction of bankruptcy of the firms and to manage the early warning and alert signal. These are the academic and empirical contribution of this study. The limitation of this research is to analyze only 100 corporates due to the difficulty of collecting the financial data of the non-audited firms, which make us to be hard to proceed to the analysis by the category or size difference. Also, non-financial qualitative data is crucial for the analysis of bankruptcy. Thus, the non-financial qualitative factor is taken into account for the next study. This study sheds some light on the non-audited small and medium sized firms' distress prediction in the future.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.195-220
• /
• 2018

In this study, we conducted an empirical analysis of the factors that affect the change of Bitcoin Closing Price. Previous studies have focused on the security of the block chain system, the economic ripple effects caused by the cryptocurrency, legal implications and the acceptance to consumer about cryptocurrency. In various area, cryptocurrency was studied and many researcher and people including government, regardless of country, try to utilize cryptocurrency and applicate to its technology. Despite of rapid and dramatic change of cryptocurrencies' price and growth of its effects, empirical study of the factors affecting the price change of cryptocurrency was lack. There were only a few limited studies, business reports and short working paper. Therefore, it is necessary to determine what factors effect on the change of closing Bitcoin price. For analysis, hypotheses were constructed from three dimensions of consumer, industry, and macroeconomics for analysis, and time series data were collected for variables of each dimension. Consumer variables consist of search traffic of Bitcoin, search traffic of bitcoin ban, search traffic of ransomware and search traffic of war. Industry variables were composed GPU vendors' stock price and memory vendors' stock price. Macro-economy variables were contemplated such as U.S. dollar index futures, FOMC policy interest rates, WTI crude oil price. Using above variables, we did times series regression analysis to find relationship between those variables and change of Bitcoin Closing Price. Before the regression analysis to confirm the relationship between change of Bitcoin Closing Price and the other variables, we performed the Unit-root test to verifying the stationary of time series data to avoid spurious regression. Then, using a stationary data, we did the regression analysis. As a result of the analysis, we found that the change of Bitcoin Closing Price has negative effects with search traffic of 'Bitcoin Ban' and US dollar index futures, while change of GPU vendors' stock price and change of WTI crude oil price showed positive effects. In case of 'Bitcoin Ban', it is directly determining the maintenance or abolition of Bitcoin trade, that's why consumer reacted sensitively and effected on change of Bitcoin Closing Price. GPU is raw material of Bitcoin mining. Generally, increasing of companies' stock price means the growth of the sales of those companies' products and services. GPU's demands increases are indirectly reflected to the GPU vendors' stock price. Making an interpretation, a rise in prices of GPU has put a crimp on the mining of Bitcoin. Consequently, GPU vendors' stock price effects on change of Bitcoin Closing Price. And we confirmed U.S. dollar index futures moved in the opposite direction with change of Bitcoin Closing Price. It moved like Gold. Gold was considered as a safe asset to consumers and it means consumer think that Bitcoin is a safe asset. On the other hand, WTI oil price went Bitcoin Closing Price's way. It implies that Bitcoin are regarded to investment asset like raw materials market's product. The variables that were not significant in the analysis were search traffic of bitcoin, search traffic of ransomware, search traffic of war, memory vendor's stock price, FOMC policy interest rates. In search traffic of bitcoin, we judged that interest in Bitcoin did not lead to purchase of Bitcoin. It means search traffic of Bitcoin didn't reflect all of Bitcoin's demand. So, it implies there are some factors that regulate and mediate the Bitcoin purchase. In search traffic of ransomware, it is hard to say concern of ransomware determined the whole Bitcoin demand. Because only a few people damaged by ransomware and the percentage of hackers requiring Bitcoins was low. Also, its information security problem is events not continuous issues. Search traffic of war was not significant. Like stock market, generally it has negative in relation to war, but exceptional case like Gulf war, it moves stakeholders' profits and environment. We think that this is the same case. In memory vendor stock price, this is because memory vendors' flagship products were not VRAM which is essential for Bitcoin supply. In FOMC policy interest rates, when the interest rate is low, the surplus capital is invested in securities such as stocks. But Bitcoin' price fluctuation was large so it is not recognized as an attractive commodity to the consumers. In addition, unlike the stock market, Bitcoin doesn't have any safety policy such as Circuit breakers and Sidecar. Through this study, we verified what factors effect on change of Bitcoin Closing Price, and interpreted why such change happened. In addition, establishing the characteristics of Bitcoin as a safe asset and investment asset, we provide a guide how consumer, financial institution and government organization approach to the cryptocurrency. Moreover, corroborating the factors affecting change of Bitcoin Closing Price, researcher will get some clue and qualification which factors have to be considered in hereafter cryptocurrency study.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.85-109
• /
• 2018

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.

• Information Systems Review
• /
• v.16 no.3
• /
• pp.161-177
• /
• 2014

Corporate credit rating assessment consists of complicated processes in which various factors describing a company are taken into consideration. Such assessment is known to be very expensive since domain experts should be employed to assess the ratings. As a result, the data-driven corporate credit rating prediction using statistical and artificial intelligence (AI) techniques has received considerable attention from researchers and practitioners. In particular, statistical methods such as multiple discriminant analysis (MDA) and multinomial logistic regression analysis (MLOGIT), and AI methods including case-based reasoning (CBR), artificial neural network (ANN), and multiclass support vector machine (MSVM) have been applied to corporate credit rating.2) Among them, MSVM has recently become popular because of its robustness and high prediction accuracy. In this study, we propose a novel optimized MSVM model, and appy it to corporate credit rating prediction in order to enhance the accuracy. Our model, named 'GAMSVM (Genetic Algorithm-optimized Multiclass Support Vector Machine),' is designed to simultaneously optimize the kernel parameters and the feature subset selection. Prior studies like Lorena and de Carvalho (2008), and Chatterjee (2013) show that proper kernel parameters may improve the performance of MSVMs. Also, the results from the studies such as Shieh and Yang (2008) and Chatterjee (2013) imply that appropriate feature selection may lead to higher prediction accuracy. Based on these prior studies, we propose to apply GAMSVM to corporate credit rating prediction. As a tool for optimizing the kernel parameters and the feature subset selection, we suggest genetic algorithm (GA). GA is known as an efficient and effective search method that attempts to simulate the biological evolution phenomenon. By applying genetic operations such as selection, crossover, and mutation, it is designed to gradually improve the search results. Especially, mutation operator prevents GA from falling into the local optima, thus we can find the globally optimal or near-optimal solution using it. GA has popularly been applied to search optimal parameters or feature subset selections of AI techniques including MSVM. With these reasons, we also adopt GA as an optimization tool. To empirically validate the usefulness of GAMSVM, we applied it to a real-world case of credit rating in Korea. Our application is in bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. The experimental dataset was collected from a large credit rating company in South Korea. It contained 39 financial ratios of 1,295 companies in the manufacturing industry, and their credit ratings. Using various statistical methods including the one-way ANOVA and the stepwise MDA, we selected 14 financial ratios as the candidate independent variables. The dependent variable, i.e. credit rating, was labeled as four classes: 1(A1); 2(A2); 3(A3); 4(B and C). 80 percent of total data for each class was used for training, and remaining 20 percent was used for validation. And, to overcome small sample size, we applied five-fold cross validation to our dataset. In order to examine the competitiveness of the proposed model, we also experimented several comparative models including MDA, MLOGIT, CBR, ANN and MSVM. In case of MSVM, we adopted One-Against-One (OAO) and DAGSVM (Directed Acyclic Graph SVM) approaches because they are known to be the most accurate approaches among various MSVM approaches. GAMSVM was implemented using LIBSVM-an open-source software, and Evolver 5.5-a commercial software enables GA. Other comparative models were experimented using various statistical and AI packages such as SPSS for Windows, Neuroshell, and Microsoft Excel VBA (Visual Basic for Applications). Experimental results showed that the proposed model-GAMSVM-outperformed all the competitive models. In addition, the model was found to use less independent variables, but to show higher accuracy. In our experiments, five variables such as X7 (total debt), X9 (sales per employee), X13 (years after founded), X15 (accumulated earning to total asset), and X39 (the index related to the cash flows from operating activity) were found to be the most important factors in predicting the corporate credit ratings. However, the values of the finally selected kernel parameters were found to be almost same among the data subsets. To examine whether the predictive performance of GAMSVM was significantly greater than those of other models, we used the McNemar test. As a result, we found that GAMSVM was better than MDA, MLOGIT, CBR, and ANN at the 1% significance level, and better than OAO and DAGSVM at the 5% significance level.