• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.1-32
• /
• 2018

In addition to stakeholders including managers, employees, creditors, and investors of bankrupt companies, corporate defaults have a ripple effect on the local and national economy. Before the Asian financial crisis, the Korean government only analyzed SMEs and tried to improve the forecasting power of a default prediction model, rather than developing various corporate default models. As a result, even large corporations called 'chaebol enterprises' become bankrupt. Even after that, the analysis of past corporate defaults has been focused on specific variables, and when the government restructured immediately after the global financial crisis, they only focused on certain main variables such as 'debt ratio'. A multifaceted study of corporate default prediction models is essential to ensure diverse interests, to avoid situations like the 'Lehman Brothers Case' of the global financial crisis, to avoid total collapse in a single moment. The key variables used in corporate defaults vary over time. This is confirmed by Beaver (1967, 1968) and Altman's (1968) analysis that Deakins'(1972) study shows that the major factors affecting corporate failure have changed. In Grice's (2001) study, the importance of predictive variables was also found through Zmijewski's (1984) and Ohlson's (1980) models. However, the studies that have been carried out in the past use static models. Most of them do not consider the changes that occur in the course of time. Therefore, in order to construct consistent prediction models, it is necessary to compensate the time-dependent bias by means of a time series analysis algorithm reflecting dynamic change. Based on the global financial crisis, which has had a significant impact on Korea, this study is conducted using 10 years of annual corporate data from 2000 to 2009. Data are divided into training data, validation data, and test data respectively, and are divided into 7, 2, and 1 years respectively. In order to construct a consistent bankruptcy model in the flow of time change, we first train a time series deep learning algorithm model using the data before the financial crisis (2000~2006). The parameter tuning of the existing model and the deep learning time series algorithm is conducted with validation data including the financial crisis period (2007~2008). As a result, we construct a model that shows similar pattern to the results of the learning data and shows excellent prediction power. After that, each bankruptcy prediction model is restructured by integrating the learning data and validation data again (2000 ~ 2008), applying the optimal parameters as in the previous validation. Finally, each corporate default prediction model is evaluated and compared using test data (2009) based on the trained models over nine years. Then, the usefulness of the corporate default prediction model based on the deep learning time series algorithm is proved. In addition, by adding the Lasso regression analysis to the existing methods (multiple discriminant analysis, logit model) which select the variables, it is proved that the deep learning time series algorithm model based on the three bundles of variables is useful for robust corporate default prediction. The definition of bankruptcy used is the same as that of Lee (2015). Independent variables include financial information such as financial ratios used in previous studies. Multivariate discriminant analysis, logit model, and Lasso regression model are used to select the optimal variable group. The influence of the Multivariate discriminant analysis model proposed by Altman (1968), the Logit model proposed by Ohlson (1980), the non-time series machine learning algorithms, and the deep learning time series algorithms are compared. In the case of corporate data, there are limitations of 'nonlinear variables', 'multi-collinearity' of variables, and 'lack of data'. While the logit model is nonlinear, the Lasso regression model solves the multi-collinearity problem, and the deep learning time series algorithm using the variable data generation method complements the lack of data. Big Data Technology, a leading technology in the future, is moving from simple human analysis, to automated AI analysis, and finally towards future intertwined AI applications. Although the study of the corporate default prediction model using the time series algorithm is still in its early stages, deep learning algorithm is much faster than regression analysis at corporate default prediction modeling. Also, it is more effective on prediction power. Through the Fourth Industrial Revolution, the current government and other overseas governments are working hard to integrate the system in everyday life of their nation and society. Yet the field of deep learning time series research for the financial industry is still insufficient. This is an initial study on deep learning time series algorithm analysis of corporate defaults. Therefore it is hoped that it will be used as a comparative analysis data for non-specialists who start a study combining financial data and deep learning time series algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2060-2077
• /
• 2019

Recently, mobile healthcare services have attracted significant attention because of the emerging development and supply of diverse wearable devices. Smartwatches and health bands are the most common type of mobile-based wearable devices and their market size is increasing considerably. However, simple value comparisons based on accumulated data have revealed certain problems, such as the standardized nature of health management and the lack of personalized health management service models. The convergence of information technology (IT) and biotechnology (BT) has shifted the medical paradigm from continuous health management and disease prevention to the development of a system that can be used to provide ground-based medical services regardless of the user's location. Moreover, the IT-BT convergence has necessitated the development of lifestyle improvement models and services that utilize big data analysis and machine learning to provide mobile healthcare-based personal health management and disease prevention information. Users' health data, which are specific as they change over time, are collected by different means according to the users' lifestyle and surrounding circumstances. In this paper, we propose a prediction model of user physical activity that uses data characteristics-based long short-term memory (DC-LSTM) recurrent neural networks (RNNs). To provide personalized services, the characteristics and surrounding circumstances of data collectable from mobile host devices were considered in the selection of variables for the model. The data characteristics considered were ease of collection, which represents whether or not variables are collectable, and frequency of occurrence, which represents whether or not changes made to input values constitute significant variables in terms of activity. The variables selected for providing personalized services were activity, weather, temperature, mean daily temperature, humidity, UV, fine dust, asthma and lung disease probability index, skin disease probability index, cadence, travel distance, mean heart rate, and sleep hours. The selected variables were classified according to the data characteristics. To predict activity, an LSTM RNN was built that uses the classified variables as input data and learns the dynamic characteristics of time series data. LSTM RNNs resolve the vanishing gradient problem that occurs in existing RNNs. They are classified into three different types according to data characteristics and constructed through connections among the LSTMs. The constructed neural network learns training data and predicts user activity. To evaluate the proposed model, the root mean square error (RMSE) was used in the performance evaluation of the user physical activity prediction method for which an autoregressive integrated moving average (ARIMA) model, a convolutional neural network (CNN), and an RNN were used. The results show that the proposed DC-LSTM RNN method yields an excellent mean RMSE value of 0.616. The proposed method is used for predicting significant activity considering the surrounding circumstances and user status utilizing the existing standardized activity prediction services. It can also be used to predict user physical activity and provide personalized healthcare based on the data collectable from mobile host devices.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.12
• /
• pp.1748-1755
• /
• 2015

A linear regression is widely used for prediction problem, but it is hard to manage an irregular nature of nonlinear system. Although nonlinear regression methods have been adopted, most of them are only fit to low and limited structure problem with small number of independent variables. However, real-world problem, such as weather prediction required complex nonlinear regression with large number of variables. GP(Genetic Programming) based evolutionary nonlinear regression method is an efficient approach to attach the challenging problem. This paper introduces the improvement of an GP based nonlinear regression method using ADF(Automatically Defined Function). It is believed ADFs allow the evolution of modular solutions and, consequently, improve the performance of the GP technique. The suggested ADF based GP nonlinear regression methods are compared with UM, MLR, and previous GP method for 3 days prediction of wind speed using MOS(Model Output Statistics) for partial South Korean regions. The UM and KLAPS data of 2007-2009, 2011-2013 years are used for experimentation.

• Communications for Statistical Applications and Methods
• /
• v.7 no.3
• /
• pp.937-943
• /
• 2000

Data mining usually deal with undesigned massive data containing many variables for which their characteristics and association rules are unknown, therefore it is actually not easy to interpret the results of analysis. In this paper, it is shown that decision tree can be very useful in interpreting data mining prediction model using two real examples.

• Journal of Information Technology Applications and Management
• /
• v.31 no.1
• /
• pp.11-25
• /
• 2024

The purpose of this study is to investigate the improvement of prediction performance and changes in variable importance in SEM-ANN two-stage analysis. 366 cosmetics repurchase-related survey data were analyzed and the results were presented. The results of this study are summarized as follows. First, in SEM-ANN two-stage analysis, SEM and ANN models were trained with train data and predicted with test data, respectively, and the R² was showed. As a result, the prediction performance was doubled from SEM 0.3364 to ANN 0.6836. Looking at this degree of R² improvement as the effect size f² of Cohen (1988), it corresponds to a very large effect at 110%. Second, as a result of comparing changes in normalized variable importance through SEM-ANN two-stage analysis, variables with high importance in SEM were also found to have high importance in ANN, but variables with little or no importance in SEM became important in ANN. This study is meaningful in that it increased the validity of the comparison by using the same learning and evaluation method in the SEM-ANN two-stage analysis. This study is meaningful in that it compared the degree of improvement in prediction performance and the change in variable importance through SEM-ANN two-stage analysis.

• The Journal of the Korea Contents Association
• /
• v.20 no.12
• /
• pp.49-57
• /
• 2020

This study predicts the ratio of added value, which represents the competitiveness of export industries in South Korea, using various machine learning techniques. To enhance the accuracy and stability of prediction, forecast combination technique was applied to predicted values of machine learning techniques. In particular, this study improved the efficiency of the prediction process by selecting key variables out of many variables using recursive feature elimination method and applying them to machine learning techniques. As a result, it was found that the predicted value by the forecast combination method was closer to the actual value than the predicted values of the machine learning techniques. In addition, the forecast combination method showed stable prediction results unlike volatile predicted values by machine learning techniques.

• The Korean Journal of Applied Statistics
• /
• v.29 no.7
• /
• pp.1257-1270
• /
• 2016

This study deals with the prediction of the total number of movie audiences as a measure for the box office. Prediction is performed by classification techniques of data mining such as decision tree, multilayer perceptron(MLP) neural network model, multinomial logit model, and support vector machine over time such as before movie release, release day, after release one week, and after release two weeks. Predictors used are: online word-of-mouth(OWOM) variables such as the portal movie rating, the number of the portal movie rater, and blog; in addition, other variables include showing the inherent properties of the film (such as nationality, grade, release month, release season, directors, actors, distributors, the number of audiences, and screens). When using 10-fold cross validation technique, the accuracy of the neural network model showed more than 90 % higher predictability before movie release. In addition, it can be seen that the accuracy of the prediction increases by adding estimates of the final OWOM variables as predictors.

• Safety and Health at Work
• /
• v.11 no.3
• /
• pp.322-334
• /
• 2020

Background: Spontaneous combustion of coal is one of the factors which causes direct or indirect gas and dust explosion, mine fire, the release of toxic gases, loss of reserve, and loss of miners' life. To avoid these incidents, the prediction of spontaneous combustion is essential. The safety of miner's in the mining field can be assured if the prediction of a coal fire is carried out at an early stage. Method: Adularya Underground Coal Mine which is fully mechanized with longwall mining method was selected as a case study area. The data collected for 2017, by sensors from ten gas monitoring stations were used for the simulation and prediction of a coal fire. In this study, the fuzzy logic model is used because of the uncertainties, nonlinearity, and imprecise variables in the data. For coal fire prediction, CO, O₂, N₂, and temperature were used as input variables whereas fire intensity was considered as the output variable.The simulation of the model is carried out using the Mamdani inference system and run by the Fuzzy Logic Toolbox in MATLAB. Results: The results showed that the fuzzy logic system is more reliable in predicting fire intensity with respect to uncertainties and nonlinearities of the data. It also indicates that the 1409 and 610/2B gas station points have a greater chance of causing spontaneous combustion and therefore require a precautional measure. Conclusion: The fuzzy logic model shows higher probability in predicting fire intensity with the simultaneous application of many variables compared with Graham's index.

• Transactions of Materials Processing
• /
• v.29 no.5
• /
• pp.241-250
• /
• 2020

In this study, the methodology of the springback prediction of automotive parts applied 3rd generation AHSS was investigated using the response surface model analysis based on a regression model, and the meta model analysis based on a Kriging model. To design the learning data set for constructing the springback prediction models, and the experimental design was conducted at three levels for each processing variable using the definitive screening designs method. The hat-shaped member, which is the basic shape of the member parts, was selected and the springback values were measured for each processing type and processing variable using the finite element analysis. When the nonlinearity of the variables is small during the hat-shaped member forming, the response surface model and the meta model can provide the same processing parameter. However, the accuracy of the springback prediction of the meta model is better than the response surface model. Even in the case of the simple shape parts forming, the springback prediction accuracy of the meta model is better than that of the response surface model, when more variables are considered and the nonlinearity effect of the variables is large. The efficient global optimization algorithm-based Kriging is appropriate in resolving the high computational complexity optimization problems such as developing automotive parts.

• The Journal of Information Systems
• /
• v.28 no.3
• /
• pp.249-276
• /
• 2019

Purpose The purpose of this study is to develop a prediction model and decision rules for the elderly's suicidal ideation based on the Korean Welfare Panel survey data. By utilizing this data, we obtained many decision rules to predict the elderly's suicide ideation. Design/methodology/approach This study used classification analysis to derive decision rules to predict on the basis of decision tree technique. Weka 3.8 is used as the data mining tool in this study. The decision tree algorithm uses J48, also known as C4.5. In addition, 66.6% of the total data was divided into learning data and verification data. We considered all possible variables based on previous studies in predicting suicidal ideation of the elderly. Finally, 99 variables including the target variable were used. Classification analysis was performed by introducing sampling technique through backward elimination and data balancing. Findings As a result, there were significant differences between the data sets. The selected data sets have different, various decision tree and several rules. Based on the decision tree method, we derived the rules for suicide prevention. The decision tree derives not only the rules for the suicidal ideation of the depressed group, but also the rules for the suicidal ideation of the non-depressed group. In addition, in developing the predictive model, the problem of over-fitting due to the data imbalance phenomenon was directly identified through the application of data balancing. We could conclude that it is necessary to balance the data on the target variables in order to perform the correct classification analysis without over-fitting. In addition, although data balancing is applied, it is shown that performance is not inferior in prediction rate when compared with a biased prediction model.