Feasibility of Deep Learning Algorithms for Binary Classification Problems (이진 분류문제에서의 딥러닝 알고리즘의 활용 가능성 평가)
-
- Journal of Intelligence and Information Systems
- /
- v.23 no.1
- /
- pp.95-108
- /
- 2017
Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.
In this study, we investigated the characteristics of participant students' modeling with the blackbox simulation program and epistemic criteria. For this research, we developed a blackbox simulation program, which is an ill-structured problem situation reflecting the scientific practice. This simulation program is applied in the activities. 23 groups, 89 second year students of an education college participated in this activity. They visualized, modeled, modified, and evaluated their thoughts on internal structure in the blackbox. All of students' activities were recorded and analyzed. As a result, the students' models in blackbox activities were categorized into four types considering their form and function. Model evaluation occurred in group model selection. Epistemic criteria such as empirical coherence, comprehensiveness, analogy, simplicity, and implementation were adapted in model evaluation. The educational implications discussed above are as follows: First, the blackbox simulation activities in which the students participated in this study have educational implications in that they provide a context in which the nature of scientific practice can be experienced explicitly and implicitly by constructing and testing models. Second, from the beginning of the activity, epistemic criteria such as empirical coherence, comprehensiveness, analogy, simplicity, and implementation were not strictly adapted and dynamically flexibly adapted according to the context. Third, the study of epistemic criteria in various contexts as well as in the context of this study will broaden the horizon of understanding the nature of scientific practice. Simulation activity, which is the context of this study, can lead to research related to computational thinking that will be more important in future society. We expect to be able to lead more discussions by furthering this study by elaborating and systematizing its context and method.
Purpose: Undertreatment of canter pain, especially due to the differences in the perception of pain between the patients and caregivers, is a well recognized problem. The purpose of this study were to determine if there exist differences in communication about pain intensity scores between patients and their family caregivers in Korea. Methods: A total of 127 patient-family caregiver dyads who have experienced canter pain participated in this study at a hospital in Seoul for six months. The data were obtained by fare to face interview with a structured questionnaire based on Brief Pain Inventory-Korean version and other previous researches. The clinical information for all patients was compiled by reviewing their medical records. Results: Patients' 'worst-pain for 24-hour' and 'right-now-pain' scores estimated by family caregivers were significantly higher than those by patient themselves. The degree of agreement between patients and family caregivers in the estimate of patients' 'worst-pain for 24-hour' intensity categories was 78.7% for 'severe pain', 40% for 'no pain', 27.5% for 'mild pain' and 22.9% for 'moderate pain'. In case of 'right-now-pain' intensity categories, the agreement was 50% for 'severe pain', 47.2% for mild pain, 46.3% for 'no pain', and 26.3% for 'moderate pain'. Conclusion: This study demonstrates that the degree of agreement between patients and family caregivers in the estimate of patients 'pain intensity categories was less than 50% except for 'severe pain'. The results indicate that Korean family caregivers tend to overestimate the canter pain intensity of their caring patients, especially, when a lancer patient has 'moderate' or 'mild pain'. Health Providers are advised to educate patient-family caregiver dyads to use a pain measurement scale to promote their agreement in pain Intensity stores. Further analyses and studies are needed to identify the factors and differences that influence their communication about pain intensity scores between patients and their family caregivers.
The recent announcement of the National Research Foundation of Korea (NRF) to cease journal accreditation operations as of the end of the year 2014 can easily influence the future of many research journals in Korea. Although this plan has not yet been formalized or structured, its facilitation would be the major turning point for the current Korean research and scholarly journals and publications. In addition, the NRF's plan to select and fund top 20 or more research journals over the five year period beginning 2015 suggests that the competition will most likely increase among Korean journals. Each journal would need to develop its unique strategy to improve and strengthen its competitiveness to become or maintain its position as a major research journal in Korea. The association of Korean Distribution of Science (KODISA) and its research journal, Journal of Distribution Science (JDS), has been continuously improving its reputation as a reputable journal in the distribution and related fields since its establishment in 1999. Due to demand, JDS has had to undergo several changes in its publication cycle first from semiannual publication to quarterly, then finally to monthly publications in 2012, and has become one of the major social science journals in Korea. Furthermore, with the redesigning of its webpage with English language in July of 2011, KODISA has made the published journals freely accessible and available to both domestic and foreign researchers, scholars, practitioners, and learners. These changes have resulted in the rapid increase in the bounce rate and the number of journal submissions by foreign scholars, with four research articles having been submitted by foreign scholars just in March of 2012 alone. However, although the changes and outcomes have resulted in a reasonable success so far, the achievement may only become a short-term success without continuously developing, improving, and implementing both effective and efficient strategies through critical, thorough, and frequent examinations and evaluations of both KODISA and JDS. As such, the purpose of this research is to carefully examine both KODISA and JDS to identify problematic factors and to develop appropriate strategies to change or modify those problems for further strengthening and improving their reputation and status. The paper examines and analyzes the past, present, and future of KODISA and JDS and their managerial, operational, and systematic procedures and operations. The narrow scope of research and inefficiencies in promoting the association and the journal and the improvement of impact factors are identified as the notable problems that could hinder JDS from being included in SCOPUS or SSCI in the near future. This type of examination and exploration has not been previously conducted, so the major limitation of this paper can be identified as not meticulously elaborating on the problems nor proving detailed recommendations based on the existing researches. This article asserted that solving the problem of the narrow scope of research would lead to facilitation of resolving other inefficient problems. Inclusion of international academic disciplines to the distribution and their related fields would be the viable initiation of expanding the research area, and this strategy could promote the journal as well as improve its impact factors. The narrow scope of research seems to be a good research topic and merit further exploration as an individual research project, because this kind of research could yield the creation of new understandings or theories.
The demographics of Internet users are the most basic and important sources for target marketing or personalized advertisements on the digital marketing channels which include email, mobile, and social media. However, it gradually has become difficult to collect the demographics of Internet users because their activities are anonymous in many cases. Although the marketing department is able to get the demographics using online or offline surveys, these approaches are very expensive, long processes, and likely to include false statements. Clickstream data is the recording an Internet user leaves behind while visiting websites. As the user clicks anywhere in the webpage, the activity is logged in semi-structured website log files. Such data allows us to see what pages users visited, how long they stayed there, how often they visited, when they usually visited, which site they prefer, what keywords they used to find the site, whether they purchased any, and so forth. For such a reason, some researchers tried to guess the demographics of Internet users by using their clickstream data. They derived various independent variables likely to be correlated to the demographics. The variables include search keyword, frequency and intensity for time, day and month, variety of websites visited, text information for web pages visited, etc. The demographic attributes to predict are also diverse according to the paper, and cover gender, age, job, location, income, education, marital status, presence of children. A variety of data mining methods, such as LSA, SVM, decision tree, neural network, logistic regression, and k-nearest neighbors, were used for prediction model building. However, this research has not yet identified which data mining method is appropriate to predict each demographic variable. Moreover, it is required to review independent variables studied so far and combine them as needed, and evaluate them for building the best prediction model. The objective of this study is to choose clickstream attributes mostly likely to be correlated to the demographics from the results of previous research, and then to identify which data mining method is fitting to predict each demographic attribute. Among the demographic attributes, this paper focus on predicting gender, age, marital status, residence, and job. And from the results of previous research, 64 clickstream attributes are applied to predict the demographic attributes. The overall process of predictive model building is compose of 4 steps. In the first step, we create user profiles which include 64 clickstream attributes and 5 demographic attributes. The second step performs the dimension reduction of clickstream variables to solve the curse of dimensionality and overfitting problem. We utilize three approaches which are based on decision tree, PCA, and cluster analysis. We build alternative predictive models for each demographic variable in the third step. SVM, neural network, and logistic regression are used for modeling. The last step evaluates the alternative models in view of model accuracy and selects the best model. For the experiments, we used clickstream data which represents 5 demographics and 16,962,705 online activities for 5,000 Internet users. IBM SPSS Modeler 17.0 was used for our prediction process, and the 5-fold cross validation was conducted to enhance the reliability of our experiments. As the experimental results, we can verify that there are a specific data mining method well-suited for each demographic variable. For example, age prediction is best performed when using the decision tree based dimension reduction and neural network whereas the prediction of gender and marital status is the most accurate by applying SVM without dimension reduction. We conclude that the online behaviors of the Internet users, captured from the clickstream data analysis, could be well used to predict their demographics, thereby being utilized to the digital marketing.
To survive in the global competitive environment, enterprise should be able to solve various problems and find the optimal solution effectively. The big-data is being perceived as a tool for solving enterprise problems effectively and improve competitiveness with its' various problem solving and advanced predictive capabilities. Due to its remarkable performance, the implementation of big data systems has been increased through many enterprises around the world. Currently the big-data is called the 'crude oil' of the 21st century and is expected to provide competitive superiority. The reason why the big data is in the limelight is because while the conventional IT technology has been falling behind much in its possibility level, the big data has gone beyond the technological possibility and has the advantage of being utilized to create new values such as business optimization and new business creation through analysis of big data. Since the big data has been introduced too hastily without considering the strategic value deduction and achievement obtained through the big data, however, there are difficulties in the strategic value deduction and data utilization that can be gained through big data. According to the survey result of 1,800 IT professionals from 18 countries world wide, the percentage of the corporation where the big data is being utilized well was only 28%, and many of them responded that they are having difficulties in strategic value deduction and operation through big data. The strategic value should be deducted and environment phases like corporate internal and external related regulations and systems should be considered in order to introduce big data, but these factors were not well being reflected. The cause of the failure turned out to be that the big data was introduced by way of the IT trend and surrounding environment, but it was introduced hastily in the situation where the introduction condition was not well arranged. The strategic value which can be obtained through big data should be clearly comprehended and systematic environment analysis is very important about applicability in order to introduce successful big data, but since the corporations are considering only partial achievements and technological phases that can be obtained through big data, the successful introduction is not being made. Previous study shows that most of big data researches are focused on big data concept, cases, and practical suggestions without empirical study. The purpose of this study is provide the theoretically and practically useful implementation framework and strategies of big data systems with conducting comprehensive literature review, finding influencing factors for successful big data systems implementation, and analysing empirical models. To do this, the elements which can affect the introduction intention of big data were deducted by reviewing the information system's successful factors, strategic value perception factors, considering factors for the information system introduction environment and big data related literature in order to comprehend the effect factors when the corporations introduce big data and structured questionnaire was developed. After that, the questionnaire and the statistical analysis were performed with the people in charge of the big data inside the corporations as objects. According to the statistical analysis, it was shown that the strategic value perception factor and the inside-industry environmental factors affected positively the introduction intention of big data. The theoretical, practical and political implications deducted from the study result is as follows. The frist theoretical implication is that this study has proposed theoretically effect factors which affect the introduction intention of big data by reviewing the strategic value perception and environmental factors and big data related precedent studies and proposed the variables and measurement items which were analyzed empirically and verified. This study has meaning in that it has measured the influence of each variable on the introduction intention by verifying the relationship between the independent variables and the dependent variables through structural equation model. Second, this study has defined the independent variable(strategic value perception, environment), dependent variable(introduction intention) and regulatory variable(type of business and corporate size) about big data introduction intention and has arranged theoretical base in studying big data related field empirically afterwards by developing measurement items which has obtained credibility and validity. Third, by verifying the strategic value perception factors and the significance about environmental factors proposed in the conventional precedent studies, this study will be able to give aid to the afterwards empirical study about effect factors on big data introduction. The operational implications are as follows. First, this study has arranged the empirical study base about big data field by investigating the cause and effect relationship about the influence of the strategic value perception factor and environmental factor on the introduction intention and proposing the measurement items which has obtained the justice, credibility and validity etc. Second, this study has proposed the study result that the strategic value perception factor affects positively the big data introduction intention and it has meaning in that the importance of the strategic value perception has been presented. Third, the study has proposed that the corporation which introduces big data should consider the big data introduction through precise analysis about industry's internal environment. Fourth, this study has proposed the point that the size and type of business of the corresponding corporation should be considered in introducing the big data by presenting the difference of the effect factors of big data introduction depending on the size and type of business of the corporation. The political implications are as follows. First, variety of utilization of big data is needed. The strategic value that big data has can be accessed in various ways in the product, service field, productivity field, decision making field etc and can be utilized in all the business fields based on that, but the parts that main domestic corporations are considering are limited to some parts of the products and service fields. Accordingly, in introducing big data, reviewing the phase about utilization in detail and design the big data system in a form which can maximize the utilization rate will be necessary. Second, the study is proposing the burden of the cost of the system introduction, difficulty in utilization in the system and lack of credibility in the supply corporations etc in the big data introduction phase by corporations. Since the world IT corporations are predominating the big data market, the big data introduction of domestic corporations can not but to be dependent on the foreign corporations. When considering that fact, that our country does not have global IT corporations even though it is world powerful IT country, the big data can be thought to be the chance to rear world level corporations. Accordingly, the government shall need to rear star corporations through active political support. Third, the corporations' internal and external professional manpower for the big data introduction and operation lacks. Big data is a system where how valuable data can be deducted utilizing data is more important than the system construction itself. For this, talent who are equipped with academic knowledge and experience in various fields like IT, statistics, strategy and management etc and manpower training should be implemented through systematic education for these talents. This study has arranged theoretical base for empirical studies about big data related fields by comprehending the main variables which affect the big data introduction intention and verifying them and is expected to be able to propose useful guidelines for the corporations and policy developers who are considering big data implementationby analyzing empirically that theoretical base.
Franchise businesses in South Korea have contributed to economic growth and job creation, and its growth potential remains very high. However, despite such virtues, domestic franchise businesses face many problems such as the instability of franchisor's business structure and weak financial conditions. To solve these problems, the government enacted legislation and strengthened franchise related laws. However, the strengthening of laws regulating franchisors had many side effects that interrupted the development of the franchise business. For example, legal regulations regarding franchisors have had the effect of suppressing the franchisor's leadership activities (e.g. activities such as the ability to advocate the franchisor's policies and strategies to the franchisees, in order to facilitate change and innovation). One of the main goals of the franchise business is to build cooperation between the franchisor and the franchisee for their combined success. However, franchisees can refuse to follow the franchisor's strategies because of the current state of franchise-related law and government policy. The purpose of this study to explore the effects of franchisor's leadership style on franchisee's commitment in a franchise system. We classified leadership styles according to the path-goal theory (House & Mitchell, 1974), and it was hypothesized and tested that the four leadership styles proposed by the path-goal theory (i.e. directive, supportive, participative and achievement-oriented leadership) have different effects on franchisee's commitment. Another purpose of this study to explore the how the level of franchisee's self-efficacy influences both the franchisor's leadership style and franchisee's commitment in a franchise system. Results of the present study are expected to provide important theoretical and practical implications as to the role of franchisor's leadership style, as restricted by government regulations and the franchisee's self-efficacy, which could be needed to improve the quality of the long-term relationship between the franchisor and franchisee. Quoted by Northouse(2007), one problem regarding the investigation of leadership is that there are almost as many different definitions of leadership as there are people who have tried to define it. But despite the multitude of ways in which leadership has been conceptualized, the following components can be identified as central to the phenomenon: (a) leadership is a process, (b) leadership involves influence, (c) leadership occurs in a group context, and (d) leadership involves goal attainment. Based on these components, in this study leadership is defined as a process whereby franchisor's influences a group of franchisee' to achieve a common goal. Focusing on this definition, the path-goal theory is about how leaders motivate subordinates to accomplish designated goals. Drawing heavily from research on what motivates employees, path-goal theory first appeared in the leadership literature in the early 1970s in the works of Evans (1970), House (1971), House and Dessler (1974), and House and Mitchell (1974). The stated goal of this leadership theory is to enhance employee performance and employee satisfaction by focusing on employee motivation. In brief, path-goal theory is designed to explain how leaders can help subordinates along the path to their goals by selecting specific behaviors that are best suited to subordinates' needs and to the situation in which subordinates are working (Northouse, 2007). House & Mitchell(1974) predicted that although many different leadership behaviors could have been selected to be a part of path-goal theory, this approach has so far examined directive, supportive, participative, and achievement-oriented leadership behaviors. And they suggested that leaders may exhibit any or all of these four styles with various subordinates and in different situations. However, due to restrictive government regulations, franchisors are not in a position to change their leadership style to suit their circumstances. In addition, quoted by Northouse(2007), ssubordinate characteristics determine how a leader's behavior is interpreted by subordinates in a given work context. Many researchers have focused on subordinates' needs for affiliation, preferences for structure, desires for control, and self-perceived level of task ability. In this study, we have focused on the self-perceived level of task ability, namely, the franchisee's self-efficacy. According to Bandura (1977), self-efficacy is chiefly defined as the personal attitude of one's ability to accomplish concrete tasks. Therefore, it is not an indicator of one's actual abilities, but an opinion of the extent of how one can use that ability. Thus, the judgment of maintain franchisee's commitment depends on the situation (e.g., government regulation and policy and leadership style of franchisor) and how it affects one's ability to mobilize resources to deal with the task, so even if people possess the same ability, there may be differences in self-efficacy. Figure 1 illustrates the model investigated in this study. In this model, it was hypothesized that leadership styles would affect the franchisee's commitment, and self-efficacy would moderate the relationship between leadership style and franchisee's commitment. Theoretically, quoted by Northouse(2007), the path-goal approach suggests that leaders need to choose a leadership style that best fits the needs of subordinates and the work they are doing. According to House & Mitchell (1974), the theory predicts that a directive style of leadership is best in situations in which subordinates are dogmatic and authoritarian, the task demands are ambiguous, and the organizational rule and procedures are unclear. In these situations, franchisor's directive leadership complements the work by providing guidance and psychological structure for franchisees. For work that is structured, unsatisfying, or frustrating, path-goal theory suggests that leaders should use a supportive style. Franchisor's Supportive leadership offers a sense of human touch for franchisees engaged in mundane, mechanized activity. Franchisor's participative leadership is considered best when a task is ambiguous because participation gives greater clarity to how certain paths lead to certain goals; it helps subordinates learn what actions leads to what outcome. Furthermore, House & Mitchell(1974) predicts that achievement-oriented leadership is most effective in settings in which subordinates are required to perform ambiguous tasks. Marsh and O'Neill (1984) tested the idea that organizational members' anger and decline in performance is caused by deficiencies in their level of effort and found that self-efficacy promotes accomplishment, decreases stress and negative consequences like depression and emotional instability. Based on the extant empirical findings and theoretical reasoning, we posit positive and strong relationships between the franchisor's leadership styles and the franchisee's commitment. Furthermore, the level of franchisee's self-efficacy was thought to maintain their commitment. The questionnaires sent to participants consisted of the following measures; leadership style was assessed using a 20 item 7-point likert scale developed by Indvik (1985), self-efficacy was assessed using a 24 item 6-point likert scale developed by Bandura (1977), and commitment was assessed using a 6 item 5-point likert scale developed by Morgan & Hunt (1994). Questionnaires were distributed to Korean optical franchisees in Seoul. It took about 20 days to complete the data collection. A total number of 140 questionnaires were returned and complete data were available from 137 respondents. Results of multiple regression analyses testing the relationships between the each of the four styles of leadership shown by the franchisor as independent variables and franchisee's commitment as the dependent variable showed that the relationship between supportive leadership style and commitment (