• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.215-229
• /
• 2020

The interest in machine learning is growing in all industries, but it is difficult to apply it to real-world tasks because of inexplicability. This paper introduces a case of developing a financial customer churn prediction model for a securities company, and introduces the research results on an attempt to develop a machine learning model that can be explained using the SHAP Value methodology and derivation of interpretability. In this study, a total of six customer churn models are compared and analyzed, and the cause of customer churn is inferred through the classification and data analysis of SHAP Value and the type of customer asset change. Based on the results of this study, it would be possible to use it as a basis for comprehensive judgment, such as using the Value of the deviation prediction result that can infer the cause of the marketing manager's actual customer marketing in the future and establishing a target marketing strategy for each customer.

• The Journal of the Korea Contents Association
• /
• v.15 no.8
• /
• pp.564-578
• /
• 2015

The present study is aimed to investigate antecedents(person-job fit, human capital investment) and outcome variable(subjective career success) of continuous-related career learning, and to demonstrate mediating effects of continuous-related career learning. The data which was applied to analysis was collected from 241 office workers who have worked for automobile company in Ulsan and public companies in Jeju and applied temporal separation of measurement as an alternative for common method bias. The results are as follows. First, person-job fit, human capital investment affected to career-related continuous learning positively. Second, the impacts of career-related continuous learning to subjective career success was positively significant. Third, the mediating effects by career-related continuous learning demonstrated statistically significant in the links between antecedents-outcome variables as partial mediation. Implications of this study contribute to expand research area of continuous-related career learning with regard to job and organizational variables, and to facilitate of research interests on subjective career success. In addition, the mechanism of career advance was empirically proved by continuous-related career learning.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.6
• /
• pp.25-32
• /
• 2012

In this paper, we proposed a development of M-learning smart-trainer content for improving the learning ability of military education. Learners of time and space constraints beyond quickly and accurately can learn with the goal, each subject by partial learning, and repetition, the whole learning quickly and easily by selecting efficiently to help you learn a m-Bizmaker with applications was designed. Experiment targets the military company of two, first aid courses were conducted for the evaluation. Traditional collective comparison group teaching methods, the proposed content, teaching methods applied in the experimental group were selected. The proposed learning applications using smart instructor for verification of learning, with which to compare, test subjects were compared with each of 49 subjects, the results p<.005 level, there was difference among the two groups. Therefore, the proposed application using a smart trainer after class proved that contribute to improving achievement.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.1
• /
• pp.229-249
• /
• 2022

This paper investigates machine learning models for predicting the designation of administrative issues in the KOSDAQ market through various techniques. When a company in the Korean stock market is designated as administrative issue, the market recognizes the event itself as negative information, causing losses to the company and investors. The purpose of this study is to evaluate alternative methods for developing a artificial intelligence service to examine a possibility to the designation of administrative issues early through the financial ratio of companies and to help investors manage portfolio risks. In this study, the independent variables used 21 financial ratios representing profitability, stability, activity, and growth. From 2011 to 2020, when K-IFRS was applied, financial data of companies in administrative issues and non-administrative issues stocks are sampled. Logistic regression analysis, decision tree, support vector machine, random forest, and LightGBM are used to predict the designation of administrative issues. According to the results of analysis, LightGBM with 82.73% classification accuracy is the best prediction model, and the prediction model with the lowest classification accuracy is a decision tree with 71.94% accuracy. As a result of checking the top three variables of the importance of variables in the decision tree-based learning model, the financial variables common in each model are ROE(Net profit) and Capital stock turnover ratio, which are relatively important variables in designating administrative issues. In general, it is confirmed that the learning model using the ensemble had higher predictive performance than the single learning model.

• Knowledge Management Research
• /
• v.14 no.5
• /
• pp.1-14
• /
• 2013

This paper is aimed at investigating the factors to grow the new technology based firm(NTBF), K-MAC. NTBFs need an environment in which novelty is encouraged, employees find work meaningful and controllable, learning is incorporated into work, ideas and process improvements are implemented and a balanced focus of the internal and external to the company is fostered. With collaboration between industry and academia, Lynda Aiman-Smith made an instrument of VIQ(Value Innovation Quotient), which is consist of 9 factors, 33 items. VIQ Results can help the company to develop a better understanding of the organization's culture, and its formal subgroups. That is to identify subcultures in the organization, to diagnose potential problems or inhibitors of innovation, to identify organizational strengths for innovation and set a quantitative baseline. Using the VIQ,K-MAC analysed the subculture of innovation potential capability. K-MAC organized the COP(community of practice) with the young employees' participation and try to solve the real problem in the working place. This paper explained the diverse growing trajectory through the TPM concept and suggest for the future strategy.

• Korean Journal of Artificial Intelligence
• /
• v.10 no.1
• /
• pp.15-19
• /
• 2022

This study is to understand the relationship between turnover and various conditions. Turnover refers to workers moving from one company to another, which exists in various ways and forms. Currently, a large number of workers are considering many turnover rates to satisfy their income levels, distance between work and residence, and age. In addition, they consider changing jobs a lot depending on the type of work, the decision-making ability of workers, and the level of education. The company needs to accept the conditions required by workers so that competent workers can work for a long time and predict what measures should be taken to convert them into long-term workers. The study was conducted because it was necessary to predict what conditions workers must meet in order to become long-term workers by comparing various conditions and turnover using regression and decision trees. It used Microsoft Azure machines to produce results, and it found that among the various conditions, it looked for different items for long-term work. Various methods were attempted in conducting the research, and among them, suitable algorithms adopted algorithms that classify various kinds of algorithms and derive results, and among them, two decision tree algorithms were used to derive results.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.2
• /
• pp.20-29
• /
• 2022

This study intends to present a traffic node-based and link-based accident prediction models using XGBoost which is very excellent in performance among machine learning models, and to develop those models with sustainability and scalability. Also, we intend to present those models which predict the number of annual traffic accidents based on road types, weather conditions, and traffic information using XGBoost. To this end, data sets were constructed by collecting and preprocessing traffic accident information, road information, weather information, and traffic information. The SHAP method was used to identify the variables affecting the number of traffic accidents. The five main variables of the traffic node-based accident prediction model were snow cover, precipitation, the number of entering lanes and connected links, and slow speed. Otherwise, those of the traffic link-based accident prediction model were snow cover, precipitation, the number of lanes, road length, and slow speed. As the evaluation results of those models, the RMSE values of those models were each 0.2035 and 0.2107. In this study, only data from Sejong City were used to our models, but ours can be applied to all regions where traffic nodes and links are constructed. Therefore, our prediction models can be extended to a wider range.

• 한국디지털정책학회:학술대회논문집
• /
• 2006.06a
• /
• pp.57-64
• /
• 2006

Arguably, the term "Learning Organisation" (LO) was coined in the 1970's, in the organisational learning context, by Chris Argyris. Certainly it has been around for many years. But it achieved new heights of popularity after the publication of Peter Senge's book "The Fifth Discipline the Art and Practice of the Learning Organisation". Now every respectable Government Agency and major company feels obliged to call themselves a L0. A review of the academic literature and organisation documents show many different concepts being described. Indeed, it seems that some organisations claiming to be a L0 have no clear idea of what they mean by the concept. This paper seeks to go behind the confusion to see whether there is still value for serious practitioners to continue using this concept, or whether it is now such a hackneyed phrase that more precise concepts are desirable. The Literature relating to the L0 is vast and it is beyond the scope of a conference presentation to give a comprehensive literature review. Instead, the paper gives an overview of the broad groups using the term and summarises their similarities and differences. It then reviews the key concepts in Senge's work in the light of this cacophony. The paper concludes that the diversity of definitions render the term "Learning Organisation" virtually meaningless. unless it is accompanied by a specific definition. The paper also concludes that the central tenet of Senge's work, which played a major role in popularising the concept, has been largely overlooked by the many organisations claiming this proud title "A Learning Organisation." It is argued that Senge's contribution to the literature in this field, the centrality of systems thinking to effective organisation learning remains a little understood, but critical insight.

• The Journal of the Korea Contents Association
• /
• v.11 no.1
• /
• pp.302-316
• /
• 2011

Despite steady economic growth of e-learning industry, manpower is lacking in e-learning industry. In this study, We developed a new e-learning business model including open market portal system to solve this problem. The existing e-learning business models required complicated procedure for creating contents. Therefore it took long time and great expense. But in this study we developed the business model with open market portal system, it can support to make easily for e-learning contents. We analysed usefulness our program and other popular programs with thirty lecturers. As a result of survey, usefulness of our system is presented. The study suggests differently the student-centered business model and the lecturer-centered business model than existing e-learning business model had the manufacturing company-centered business model and the services-centered business model. We anticipate the new business model invigorate the e-learning industry.

• Journal of Korea Technology Innovation Society
• /
• v.14 no.3
• /
• pp.647-663
• /
• 2011

Company's interest in the work place training and investment has been growing continuously because the talent of human resource is the competitiveness itself in the knowledge based society. However, corporate training programs mainly have focused on large companies and SMEs despite the economic business volume have been treated too lightly so far. This paper regards corporate training programs with one of the methods for SMEs innovation and proposes the smart learning in the smart device diffusion. Concretely, this paper analyzes the utilization intention, each attribute and level in smart learning characteristics using conjoint analysis. The result shows that SMEs have positive response for smart learning acceptance and SMEs consider significantly the usage fee type and location with the difference between regular employee and administrator. Specially, interactive communication and customized contents are preferred in the training type. Smart learning can be used as strategic means in supporting the value innovation and enhancing the absorptive capacity in SMEs innovation process.