• Journal of applied mathematics & informatics
• /
• v.39 no.1_2
• /
• pp.239-249
• /
• 2021

This study attempts to predict the price of gold futures, a real financial product, using ARIMA and LSTM. The wavelet analysis was applied to the data to predict the price of gold futures through LSTM and ARIMA. As results, it is confirmed that the prediction performance of the existing model of predict was improved. the case of predict of price of gold futures, we confirmed that the use of a deep learning model that is not affected by the non-stationary series data is suitable and the possibility of improving the accuracy of prediction through wavelet analysis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.435-438
• /
• 2020

시장예측 문제를 해결하기 위하여 과거부터 꾸준한 연구가 진행되어왔다. 하지만 금융 시계열 데이터에는 분산이 일정하지 않으며 Non-stationarity 등 예측을 하는 것에 있어서 여러 가지 방해 요인이 존재한다. 또한 광범위한 데이터 변수는 기존에 사람이 직접 경험적으로 선택하는 것에 한계가 있기 때문에, 모델이 변수를 자동으로 추출할 수 있어야 한다. 본 논문에서는 여러 가지 금융 시계열 데이터의 문제를 고려하여 타임 스텝 정규화를 제안하며 자동 변수 추출을 위해 LSTM 형태의 오토 인코더 모델을 학습하였으며 LSTM 네트워크를 이용하여 시장 예측하는 모델을 제안한다. 해당 시스템은 실제 주식 거래나 시장 거래를 위하여 온라인 학습이 가능하며 긴 기간을 테스트 구간으로 실험한 결과 미래의 수익률을 예측하는 것에 있어서 우수한 성능을 보였다.

• Journal of Convergence Society for SMB
• /
• v.1 no.1
• /
• pp.1-8
• /
• 2011

With a sample of 147 Korean small and medium size companies, this study examined the relationships among degree of information orientation, corporate culture, degree of information management implementation and selected business performances in the process of implementing IMS(Information Management System). Information orientation is defined as company-wide understanding and implementation of the underlying philosophy, principles, approached, and tools of information improvement programs. It is assumed that successful implementation of information improvement programs requires a information-oriented mind-set of the employees. It is also assumed that successful implementation of information improvement programs require strong support from s corporate culture that emphasizes continues improvement. Adopting the competing values model of Quinn and McGrath(1985), corporate culture is classified into 'flexible' versus 'controlled culture' and 'outer-directed' versus 'inner-directed culture'. This study examined how such fitness influenced the implementation of information innovation programs and business performance. Implementation of information innovation programs was measured through various factors, such as leadership, strategic information planning, human resources focus, customer and market focus, process management, and information analysis and application. Business performance was measured through non-financial performance measuresm such as employee results, process results, information results, and customer results, and through perceived financial performance measures.

• Journal of Distribution Research
• /
• v.15 no.4
• /
• pp.87-117
• /
• 2010

'Entrepreneurship' which means spirit or activity seeking new value by challenging boldly the uncertainty is one of the most important concept in 21st century business environment. Franchise Industry taking a relationship with distribution industry also needs entrepreneurship. As franchise industry consists of small and medium enterprises, the entrepreneurship of franchisor's CEO is important for the franchisor's growth. The purpose of this study is to analyze the factors influencing on the entrepreneurship of franchisor's CEO, and the effect of the CEO's entrepreneurship on franchisor's performance. For this purpose, this study set CEO's psychological characteristics, market characteristics, and social-institutional characteristics as independent variables, CEO's entrepreneurship as parameter variables, and franchisor's performance as dependent variables. And to analyze this study model, this study collected questionnaires from 152 franchisors' CEOs, and uses SEM(Structural Equation Modeling). As the result, 'CEO's Entrepreneurship' influenced on both 'Franchisor's Financial Performance' and 'Franchisor's Non Financial Performance'. The results of this study provide some guides for franchisor's CEO and government policies.

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.139-157
• /
• 2016

Bankruptcy involves considerable costs, so it can have significant effects on a country's economy. Thus, bankruptcy prediction is an important issue. Over the past several decades, many researchers have addressed topics associated with bankruptcy prediction. Early research on bankruptcy prediction employed conventional statistical methods such as univariate analysis, discriminant analysis, multiple regression, and logistic regression. Later on, many studies began utilizing artificial intelligence techniques such as inductive learning, neural networks, and case-based reasoning. Currently, ensemble models are being utilized to enhance the accuracy of bankruptcy prediction. Ensemble classification involves combining multiple classifiers to obtain more accurate predictions than those obtained using individual models. Ensemble learning techniques are known to be very useful for improving the generalization ability of the classifier. Base classifiers in the ensemble must be as accurate and diverse as possible in order to enhance the generalization ability of an ensemble model. Commonly used methods for constructing ensemble classifiers include bagging, boosting, and random subspace. The random subspace method selects a random feature subset for each classifier from the original feature space to diversify the base classifiers of an ensemble. Each ensemble member is trained by a randomly chosen feature subspace from the original feature set, and predictions from each ensemble member are combined by an aggregation method. The k-nearest neighbors (KNN) classifier is robust with respect to variations in the dataset but is very sensitive to changes in the feature space. For this reason, KNN is a good classifier for the random subspace method. The KNN random subspace ensemble model has been shown to be very effective for improving an individual KNN model. The k parameter of KNN base classifiers and selected feature subsets for base classifiers play an important role in determining the performance of the KNN ensemble model. However, few studies have focused on optimizing the k parameter and feature subsets of base classifiers in the ensemble. This study proposed a new ensemble method that improves upon the performance KNN ensemble model by optimizing both k parameters and feature subsets of base classifiers. A genetic algorithm was used to optimize the KNN ensemble model and improve the prediction accuracy of the ensemble model. The proposed model was applied to a bankruptcy prediction problem by using a real dataset from Korean companies. The research data included 1800 externally non-audited firms that filed for bankruptcy (900 cases) or non-bankruptcy (900 cases). Initially, the dataset consisted of 134 financial ratios. Prior to the experiments, 75 financial ratios were selected based on an independent sample t-test of each financial ratio as an input variable and bankruptcy or non-bankruptcy as an output variable. Of these, 24 financial ratios were selected by using a logistic regression backward feature selection method. The complete dataset was separated into two parts: training and validation. The training dataset was further divided into two portions: one for the training model and the other to avoid overfitting. The prediction accuracy against this dataset was used to determine the fitness value in order to avoid overfitting. The validation dataset was used to evaluate the effectiveness of the final model. A 10-fold cross-validation was implemented to compare the performances of the proposed model and other models. To evaluate the effectiveness of the proposed model, the classification accuracy of the proposed model was compared with that of other models. The Q-statistic values and average classification accuracies of base classifiers were investigated. The experimental results showed that the proposed model outperformed other models, such as the single model and random subspace ensemble model.

• The Korean Journal of Emergency Medical Services
• /
• v.7 no.1
• /
• pp.213-234
• /
• 2003

The purposes of this study which was done by questionnaire survey and case study of First Aid Certification Program in Seoul Health College were to analyze results and effects of the college financial support program from Ministry of Education & Human Resources Development. The significant 164 data were collected from 300 professors in 8 colleges having the Department of Emergency Care from Oct. 1, 2002 to Dec. 31, 2002 and analyzed using SPSS in terms of t-test, ANOVA, Pearson's correlation coefficient and so on. The conclusions and suggestions from this study were summarized as follows; (1) Degree of acknowledgement about aims, contents, results of the college financial support program was above the middle(participants 4.21, non-participants 3.63) and higher relation than the others in case of participants(r:0.32 p<0.001), planning team(r:0.22 p<0.05). (2) Degree of acknowledgement about improvement of curriculum & educational facilities through the program was above the middle and higher relation than the others in case of participants. (3) Degree of acknowledgement about positive influence on acquirement rate of certification(licence) & job through the program was above the middle and performance & adaptation at work place was higher relation than the others in case of participants. (4) Degree of acknowledgement about positive influence on improvement of learning of student's major through the program was above the middle and higher relation than the others in case of participants. (5) The respondents thought that the program had a negative influence on professor's educational activities & research such as study 40.4%, lecture 23.1%, student guidance 12.5%. (6) When the program was administered by planning team, there were difficulties such as execution of budget 42.1%, cooperation with companies 17.1%, cooperation among program teams 11.8%, when it was administered by non-planning team there were difficulties such as execution of budget 45.5%, cooperation among departments 22.7%, cooperation with companies 13.6%. (7) Because it was too short to execute the budget, the ministry have to select proposed programs before the next school year. (8) This program should be changed temporary, insufficient support into consecutive, sufficient support for more characterization & specialization of the college which has a long-term developmental plan & vision.

• Information Systems Review
• /
• v.20 no.4
• /
• pp.79-96
• /
• 2018

This study started by focusing on the internalization of the technology appraisal model into the credit rating model to increase the discriminative power of the credit rating model not only for SMEs but also for all companies, reflecting the items related to the financial stability of the enterprises among the technology appraisal items. Therefore, it is aimed to verify whether the technology appraisal model can be applied to identify high-stability SMEs in advance. We classified companies into industries (manufacturing vs. non-manufacturing) and the age of company (initial vs. non-initial), and defined as a high-stability company that has achieved an average debt ratio less than 1/2 of the group for three years. The C5.0 was applied to verify the discriminant power of the model. As a result of the analysis, there is a difference in importance according to the type of industry and the age of company at the sub-item level, but in the mid-item level the R&D capability was a key variable for discriminating high-stability SMEs. In the early stage of establishment, the funding capacity (diversification of funding methods, capital structure and capital cost which taking into account profitability) is an important variable in financial stability. However, we concluded that technology development infrastructure, which enables continuous performance as the age of company increase, becomes an important variable affecting financial stability. The classification accuracy of the model according to the age of company and industry is 71~91%, and it is confirmed that it is possible to identify high-stability SMEs by using technology appraisal items.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.12 no.4
• /
• pp.47-60
• /
• 2017

As the recent cultural contents area start-ups are creating remarkable outcomes such as investment attraction together with the reinforced institutional supports from the government, this study aimed to reverify the significance of researches related to correlation analysis between service of Business Incubating Center of Small & Medium Business Administration operated with no separation of business type, and corporate performance, in the aspect of Business Incubating Center in cultural contents area, and also to suggest the importance of establishing the business incubating system in the systematic and rational cultural contents area through the differentiated business incubating service by verifying the significant effects of the business validity of items on corporate performance, and then discovering services suitable for business incubating in cultural contents area, targeting Gyeonggi-do cultural contents area Business Incubating Center recently showing the biggest growth. Especially, contrary to the existing researches, in order to verify the characteristics of Gyeonggi-do Cultural Contents Business Incubating Center, the personal support service and marketing support service were included. It also aimed to understand the effects of the business validity of start-up items on corporate performance. Summarizing the results of this study, contrary to the results of the existing researches saying that spatial & additional support service, management support service, technical support service, personal support service, and marketing support service had significant effects on corporate performance, among the support service of Gyeonggi-do cultural contents area Business Incubating Center, the spatial & additional support service, personal support service, and marketing support service had significantly positive(+) effects on corporate performance while the management support service and technical support service had no significant effects on it. Comparing with the results of the researches on the support service of Business Incubating Center(BI) of Small & Medium Business Administration, the effects of the management support service and technical support service of Gyeonggi-do cultural contents area Business Incubating Center on corporate financial/non-financial performance were not huge. Also, in the results of analyzing the business validity of star-up items, the spatial & additional support service, management support service, and technical support service did not have significant effects on the business validity of start-up items while the personal support service and marketing support service had significantly positive(+) effects on it. In case when selecting companies, Gyeonggi-do Business Incubating Center emphasized the business validity of start-up items. However, the support service provided after the selection did not have huge effects on the business validity of start-up items. Lastly, in the results of analyzing the effects of the business validity of start-up items in Gyeonggi-do cultural contents area on corporate performance, among the success factors of business start-up, the business validity of start-up items was an important element having effects on corporate performance(financial/non-financial) in the cultural contents area.

• Journal of Korean Society of Forest Science
• /
• v.99 no.5
• /
• pp.655-662
• /
• 2010

Desertification has been expanding with a remarkable speed across the Northeast Asia. Desertification in Northeast Asia significantly influences Korea's economy and environmental health conditions in recent years. For these reasons, a number of non-governmental organizations (NGOs) in Korea have carried out the reforestation projects to combat desertification in China and Mongolia. Several tree plantation projects were implemented in Mongolia and China. The objective of this study was to analyze and evaluate the performance of tree plantation aid projects carried out by Korean NGOs in Mongolia. The performance of tree plantation projects was examined through effectiveness, efficiency, equity and responsiveness of those projects. The performance was analyzed with the survival rate of planted trees and planting cost, the recognitions of Mongolian people. The analysis of the performance showed that the tree plantation cooperation projects carried out by Korean NGOs in Mongolia had comparatively high performance from a larger point of view. Especially, effectiveness and responsiveness of their projects were highly marked in spite of all the difficulties of carrying out the tree plantation. Such a high effectiveness represented the relatively higher survival rates of trees and Mongolian's positive recognition of plantation projects. Furthermore, the responsiveness also turned out to be high with a great satisfaction of the Mongolian people for plantation projects conducted by the Korean NGOs. Survey results indicated that the efficiency and equity of the projects would be increased by promoting the cooperation projects for tree planting throughout Mongolia with reinforcing infrastructures. By comparison between Korean NGOs and Mongolian Government plantation projects, confirmed the importance of sustained financial support and maintenance activities in the plantation sites.

• The Journal of Asian Finance, Economics and Business
• /
• v.4 no.2
• /
• pp.19-23
• /
• 2017

It is undisputable that crude oil and its price fluctuations are major components that affect most of the countries' economies. Recent studies have demonstrated that beside the impact that crude oil price fluctuations have on common macroeconomic indicators like gross domestic product (GDP), inflation rates, exchange rates, unemployment rate, etc., it also has a strong influence on stock markets and their performance. This relationship has been examined in a number of settings, but it is yet to be unraveled in the Omani context. Accordingly, the main purpose of this study is to examine the possible effect of the oil price fluctuations on stock price movements. The study applies Toda and Yamamoto's (1995) Granger non-causality test on the daily Oman stock index (Muscat Securities Market Index) and oil prices between the period of 2 January 2003 and 13 March 2016. The results indicated that the oil price fluctuations have a significant impact on stock index movements. However, the stock price movements do not have a significant impact on oil prices. These findings have significant implications not only for the Omani economy but also for the economy of similar countries, particularly in the Gulf Cooperation Council (GCC) countries. The latter should carefully consider their policies and strategies regarding crude oil production and the generated income allocation as it might potentially affect the financial markets performance in these countries.