• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.487-492
• /
• 2018

4차산업 혁명의 여파로 국내에서는 다양한 분야에 인공지능과 빅데이터 기술을 활용하여 이전에 시행 중인 다양한 서비스 분야에 기술적 접목과 보완을 시도하고 있다. 특히 금융권에서 자금을 빌린 기업들을 대상으로 여신 안정성을 확보하고 선제적인 대응을 위해 온라인 뉴스기사들과 SNS 데이터 등을 이용하여 부실가능성을 예측하고 실제 업무에 도입하려는 시도들이 국내 주요 은행들을 중심으로 활발히 진행 중이다. 우리는 국내의 국책은행에서 수행한 비정형 데이터 기반의 기업의 부실징후 예측 시스템 개발 과정에서 시도된 다양한 분석 방법과 결과 그리고 과정 중에 발생한 문제점들에 관해 기술하고 관련 이슈들에 관하여 다룬다. 결과적으로 본 논문은 레이블이 없는 대량의 기사들에 레이블을 달기 위한 자동 태거(tagger) 개발과 뉴스 기사 예측 결과로부터 부실 가능성을 예측하기 위한 모델 및 성능 면에서 기사 예측 정확도 92%(AUC 0.96) 및 부실 가능성 기업 예측에서도 정형 데이터 분석결과에 견줄만한 성과를 이루었고 이에 관해 보고한다.

• The Korean Journal of Applied Statistics
• /
• v.32 no.6
• /
• pp.795-835
• /
• 2019

Big data has been generated in various fields. Many companies have now tried to make profits by building a system capable of analyzing big data based on artificial intelligence (AI) techniques. Integrating AI technology has made analyzing and utilizing vast amounts of data increasingly valuable. In particular, demand forecasting with maximum accuracy is critical to government and business management in various fields such as finance, procurement, production and marketing. In this case, it is important to apply an appropriate model that considers the demand pattern for each field. It is possible to analyze complex patterns of real data that can also be enlarged by a traditional time series model or regression model. However, choosing the right model among the various models is difficult without prior knowledge. Many studies based on AI techniques such as machine learning and deep learning have been proven to overcome these problems. In addition, demand forecasting through the analysis of stereotyped data and unstructured data of images or texts has also shown high accuracy. This paper introduces important areas where demand forecasts are relatively active as well as introduces machine learning and deep learning techniques that consider the characteristics of each field.

• Knowledge Management Research
• /
• v.25 no.2
• /
• pp.19-47
• /
• 2024

Organizational ability to analyze and utilize data plays an important role in knowledge management and decision-making. This study aims to investigate the potential application of large language models in corporate data analysis. Focusing on the field of human resources, the research examines the data analysis capabilities of these models. Using the widely studied IBM HR dataset, the study reproduces machine learning-based employee turnover prediction analyses from previous research through ChatGPT and compares its predictive performance. Unlike past research methods that required advanced programming skills, ChatGPT-based machine learning data analysis, conducted through the analyst's natural language requests, offers the advantages of being much easier and faster. Moreover, its prediction accuracy was found to be competitive compared to previous studies. This suggests that large language models could serve as effective and practical alternatives in the field of corporate data analysis, which has traditionally demanded advanced programming capabilities. Furthermore, this approach is expected to contribute to the popularization of data analysis and the spread of data-driven decision-making (DDDM). The prompts used during the data analysis process and the program code generated by ChatGPT are also included in the appendix for verification, providing a foundation for future data analysis research using large language models.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.85-100
• /
• 2023

Corporate ESG performance (environmental, social, and corporate governance) reflecting a company's strategic sustainability has emerged as one of the main factors in today's investment decisions. The traditional ESG performance rating process is largely performed in a qualitative and subjective manner based on the institution-specific criteria, entailing limitations in reliability, predictability, and timeliness when making investment decisions. This study attempted to predict the corporate ESG rating through automated machine learning based on quantitative and disclosed corporate financial information. Using 12 types (21,360 cases) of market-disclosed financial information and 1,780 ESG measures available through the Korea Institute of Corporate Governance and Sustainability during 2019 to 2021, we suggested a deep neural network prediction model. Our model yielded about 86% of accurate classification performance in predicting ESG rating, showing better performance than other comparative models. This study contributed the literature in a way that the model achieved relatively accurate ESG rating predictions through an automated process using quantitative and publicly available corporate financial information. In terms of practical implications, the general investors can benefit from the prediction accuracy and time efficiency of our proposed model with nominal cost. In addition, this study can be expanded by accumulating more Korean and international data and by developing a more robust and complex model in the future.

• Management & Information Systems Review
• /
• v.37 no.3
• /
• pp.1-25
• /
• 2018

This research performed the empirical test for the effects of learning transfer on perceived usefulness, perceived ease of use, self-efficacy and work environment using 390 employees who have experienced e-learning in domestic and foreign companies. Analyzed the mediating effects of self-efficacy and work environment in addition to direct effect of each factor on learning transfer. The results showed that perceived usefulness and perceived ease-of-use of e-learning learner had a positive(＋) effect on self-efficacy and a positive influence on supervisor and peer support and organizational climate. Self-efficacy showed a positive effect on learning transfer, and supervisor support, peer support and organizational climate had a positive influence on learning transfer as well. Perceived usefulness also had a positive effect on learning transfer. However, perceived ease-of-use had no significant effect on learning transfer. As a result of the mediating effect analysis, self-efficacy and work environment were analyzed to have mediating effects between perceived usefulness, perceived ease of use, and learning transfer. The implications of this study are as follows. First, this study designed a new research model that reflects factors influencing the effect of learning transfer on acceptance of e-learning that is common in corporate education. It has derived a research model of perceived usefulness and perceived ease-of-use, which were used as mediating variables for external characteristics factors, as independent variables, using self-efficacy and work environment as mediating variables, which were studied as external factors. Second, most of the studies on technology acceptance model and learning transfer are conducted in a single country. The reliability was enhanced by testing the study models using different samples from 26 countries. Third, perceived usefulness and ease-of-use in existing studies have been considered as key determinants of acceptance intention and learning transfer. This study explored the mediating effects of learner and environmental factors on the accepted information technology and strengthened and supplemented the path of learning transfer of perceived usefulness and ease-of-use. In addition, based on the sample analysis of various countries used in this study, it is expected that future international comparative studies will be possible.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.781-784
• /
• 2019

최근 AI를 산업 서비스에 적용하기 위해 많은 회사들이 활발히 연구를 하고 있다. 아마존과 넷플릭스 같은 거대 기업들은 이미 빅데이터와 AI 머신러닝을 이용한 추천 시스템을 구현하였고 아마존은 매출의 35%가 추천에 의해 발생하고 넷플릭스 75%의 사용자가 추천을 통해 영화를 선택한다고 보고되었다. 이러한 두 기업의 높은 추천 효율성의 이유는 협업 필터링(Collaborative filtering)과 같은 다양한 추천 알고리즘과 방대한 상품 및 고객 행동(구매, 시청 등) 데이터 등이 존재하고 있기 때문이다. 기계학습에서 알고리즘 학습을 위한 데이터의 양이 많지 않을 경우 알고리즘의 성능을 보장할 수 없다는 것이 일반적인 의견이다. 방대한 데이터를 가진 기업에서 추천 알고리즘을 적극적으로 활용 및 연구하고 있는 것도 이러한 이유 때문이다. 반면, 오프라인 및 여행사 기반에서 온라인 기반으로 영역을 차츰 확대하고 있는 항공 서비스 고객 데이터의 경우, 산업의 특성상 많은 회원에 비해 고객 1명당 온라인에서 활동하는 이력이 많지 않은 것이 특징이다. 이는, 추천 알고리즘을 통한 서비스 제공에서 큰 제약사항으로 작용한다. 본 연구에서는, 이러한 희박한 고객 활동 데이터에서 최신성 기반의 추천 시스템을 통하여 제약사항을 극복하고 추천 효율을 높이는 방법을 제안한다. 고객의 최근 접속 이력 로그를 시간 기준으로 데이터 셋을 분할하여 추천 알고리즘에 반영하였을 때, 추천된 노선에 대한 고객의 반응을 추천 성능 지표인 CTR(Click-Through Rate)로 측정하여 성능을 확인해 보았다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.711-713
• /
• 2023

딥러닝 기반 성별 및 연령 추정은 현재 다양한 응용분야에 적용하기 위하여 활발히 연구되어 왔다. 최근 몇몇 기업에서는 개인정보 보호의 문제로 성별 추정 서비스를 중단하고 있기는 하나, 사용자 및 관람객의 특성 분석등을 위하여 그 필요성이 계속하여 대두되고 있는 상황이다. 본 논문은 기존에 성별 및 나이 추정을 위한 유료서비스에 대한 특성과 사용 문제점 등을 세분화하여 조사하고 성별 및 연령 추정 기반 기존 연구들의 특성을 분석한다. 추후 이 서비스를 기반으로 전시 · 컨벤션 산업에서의 관심도 분석 및 재방문 의사를 파악하는데 활용하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.443-446
• /
• 2019

빅데이터 분석을 위해 많이 사용하고 있는 기계학습 알고리즘들 중 딥러닝 알고리즘이 많이 활용되고 있으며 분류와 예측에 높은 정확도를 나타내고 있다. 딥러닝 알고리즘의 적용에 따른 많은 장단점들이 있지만, 단점은 분석에 사용되는 특징들이 너무 많다는 것과 분석 모델을 만드는데 사용되는 알고리즘도 여러 가지를 적용하다 보니 분석 시간이 오래 걸린다는 것이다. 이런 단점들은 업무를 파악하면 특징을 최소화할 수 있고 필요로 하는 정보만 선별해서 대표적인 딥러닝 알고리즘 하나에 분석을 하게 되면 분석 시간을 단축시킬 수 있다. 이 실험은 [1], [2]에서 연구한 영화 관객수 예측 모델을 4개의 특징으로 최소화하고 선별된 데이터를 인공신경망 알고리즘 하나로 예측 모델을 생성하였을 때 유의미한 정보를 도출해 낼 수 있는지를 알아보기 위한 것이다. 실험결과는 최종 관객수를 1명 단위까지 정확하게 예측하지는 못했지만 비슷한 수준의 관객수 정보를 예측하였다. 학문적인 접근으로 보았을 때 예측 정확도가 높지 않으면 사용이 불가능한 모델이라고 판단할 수 있지만, 기업 입장으로 접근해 보았을 때 예측 정보가 [1]. [2] 연구 결과에 비해 부족한 수준은 아니다. 총 소요된 시간은 기획 3일, 데이터 수집 및 모델 개발 5일, 분석 시간 10분으로 개발 시간 단축, 업무 효율성 향상, 비용 절감을 기대할 수 있다.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.137-142
• /
• 2021

Although the internet has gained many conveniences and benefits, it is causing economic and social damage to users due to intelligent malware. Most of the signature-based anti-virus programs are used to detect and defend this, but it is insufficient to prevent malware variants becoming more intelligent. Therefore, we proposes a model that detects and defends the intelligent malware that is pouring out in the paper. The proposed model learns by imaging the characteristics of malware based on deeplearning, and detects newly detected malware variants using the learned model. It was shown that the proposed model detects not only the existing malware but also most of the variants that transform the existing malware.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.203-210
• /
• 2022

As more and more research and companies use health care data, efforts are being made to vitalize health care data worldwide. However, the system and format used by each institution is different. Therefore, this research established a basic model to classify text data onto multiple institutions according to the type of the future by establishing a basic model to classify the types of medical records of the EEG Report. For EEG Report classification, four deep learning-based algorithms were compared. As a result of the experiment, the ANN model trained by vectorizing with One-Hot Encoding showed the highest performance with an accuracy of 71%.