• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.251-273
• /
• 2022

Recently, research on applying text analysis to deep learning has steadily continued. In particular, researches have been actively conducted to understand the meaning of words and perform tasks such as summarization and sentiment classification through a pre-trained language model that learns large datasets. However, existing pre-trained language models show limitations in that they do not understand specific domains well. Therefore, in recent years, the flow of research has shifted toward creating a language model specialized for a particular domain. Domain-specific pre-trained language models allow the model to understand the knowledge of a particular domain better and reveal performance improvements on various tasks in the field. However, domain-specific further pre-training is expensive to acquire corpus data of the target domain. Furthermore, many cases have reported that performance improvement after further pre-training is insignificant in some domains. As such, it is difficult to decide to develop a domain-specific pre-trained language model, while it is not clear whether the performance will be improved dramatically. In this paper, we present a way to proactively check the expected performance improvement by further pre-training in a domain before actually performing further pre-training. Specifically, after selecting three domains, we measured the increase in classification accuracy through further pre-training in each domain. We also developed and presented new indicators to estimate the specificity of the domain based on the normalized frequency of the keywords used in each domain. Finally, we conducted classification using a pre-trained language model and a domain-specific pre-trained language model of three domains. As a result, we confirmed that the higher the domain specificity index, the higher the performance improvement through further pre-training.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.41-59
• /
• 2022

The timely procurement of military supplies is essential to maintain the military's operational capabilities, and contract work is the first step toward timely procurement. In addition, rapid signing of a contract enables consumers to set a leisurely delivery date and increases the possibility of budget execution, so it is essential to improve the contract process to prevent early execution of the budget and transfer or disuse. Recently, research using big data has been actively conducted in various fields, and process analysis using big data and process mining, an improvement technique, are also widely used in the private sector. However, the analysis of contract work in the military is limited to the level of individual analysis such as identifying the cause of each problem case of budget transfer and disuse contracts using the experience and fragmentary information of the person in charge. In order to improve the contract process, this study analyzed using the process mining technique with data on a total of 560 contract tasks directly contracted by the Department of Finance of the Air Force Logistics Command for about one year from November 2019. Process maps were derived by synthesizing distributed data, and process flow, execution time analysis, bottleneck analysis, and additional detailed analysis were conducted. As a result of the analysis, it was found that review/modification occurred repeatedly after request in a number of contracts. Repeated reviews/modifications have a significant impact on the delay in the number of days to complete the cost calculation, which has also been clearly revealed through bottleneck visualization. Review/modification occurs in more than 60% of the top 5 departments with many contract requests, and it usually occurs in the first half of the year when requests are concentrated, which means that a thorough review is required before requesting contracts from the required departments. In addition, the contract work of the Department of Finance was carried out in accordance with the procedures according to laws and regulations, but it was found that it was necessary to adjust the order of some tasks. This study is the first case of using process mining for the analysis of contract work in the military. Based on this, if further research is conducted to apply process mining to various tasks in the military, it is expected that the efficiency of various tasks can be derived.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.249-263
• /
• 2023

Collaborative Filtering, a representative recommendation system methodology, consists of two approaches: neighbor methods and latent factor models. Among these, the latent factor model using matrix factorization decomposes the user-item interaction matrix into two lower-dimensional rectangular matrices, predicting the item's rating through the product of these matrices. Due to the factor vectors inferred from rating patterns capturing user and item characteristics, this method is superior in scalability, accuracy, and flexibility compared to neighbor-based methods. However, it has a fundamental drawback: the need to reflect the diversity of preferences of different individuals for items with no ratings. This limitation leads to repetitive and inaccurate recommendations. The Adaptive Deep Latent Factor Model (ADLFM) was developed to address this issue. This model adaptively learns the preferences for each item by using the item description, which provides a detailed summary and explanation of the item. ADLFM takes in item description as input, calculates latent vectors of the user and item, and presents a method that can reflect personal diversity using an attention score. However, due to the requirement of a dataset that includes item descriptions, the domain that can apply ADLFM is limited, resulting in generalization limitations. This study proposes a Generalized Adaptive Deep Latent Factor Recommendation Model, G-ADLFRM, to improve the limitations of ADLFM. Firstly, we use item ID, commonly used in recommendation systems, as input instead of the item description. Additionally, we apply improved deep learning model structures such as Self-Attention, Multi-head Attention, and Multi-Conv1D. We conducted experiments on various datasets with input and model structure changes. The results showed that when only the input was changed, MAE increased slightly compared to ADLFM due to accompanying information loss, resulting in decreased recommendation performance. However, the average learning speed per epoch significantly improved as the amount of information to be processed decreased. When both the input and the model structure were changed, the best-performing Multi-Conv1d structure showed similar performance to ADLFM, sufficiently counteracting the information loss caused by the input change. We conclude that G-ADLFRM is a new, lightweight, and generalizable model that maintains the performance of the existing ADLFM while enabling fast learning and inference.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.307-325
• /
• 2023

Due to the prolonged COVID-19 pandemic, the frequency of people who are tired of living indoors visiting nearby mountains and national parks to relieve depression and lethargy has exploded. There is a place where thousands of people who came out of nature stop walking and breathe and rest, that is the mineral spring. Even in mountains or national parks, there are about 600 mineral springs that can be found occasionally in neighboring parks or trails in the metropolitan area. However, due to irregular and manual water quality tests, people drink mineral water without knowing the test results in real time. Therefore, in this study, we intend to develop a model that can predict the quality of the spring water in real time by exploring the factors affecting the quality of the spring water and collecting data scattered in various places. After limiting the regions to Seoul and Gyeonggi-do due to the limitations of data collection, we obtained data on water quality tests from 2015 to 2020 for about 300 mineral springs in 18 cities where data management is well performed. A total of 10 factors were finally selected after two rounds of review among various factors that are considered to affect the suitability of the mineral spring water quality. Using AutoML, an automated machine learning technology that has recently been attracting attention, we derived the top 5 models based on prediction performance among about 20 machine learning methods. Among them, the catboost model has the highest performance with a prediction classification accuracy of 75.26%. In addition, as a result of examining the absolute influence of the variables used in the analysis through the SHAP method on the prediction, the most important factor was whether or not a water quality test was judged nonconforming in the previous water quality test. It was confirmed that the temperature on the day of the inspection and the altitude of the mineral spring had an influence on whether the water quality was unsuitable.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.361-381
• /
• 2023

Research on corporate bankruptcy prediction has been focused on financial information. Since the company's financial information is updated quarterly, there is a problem that timeliness is insufficient in predicting the possibility of a company's business closure in real time. Evaluated companies that want to improve this need a method of judging the soundness of a company that uses information other than financial information to judge the soundness of a target company. To this end, as information technology has made it easier to collect non-financial information about companies, research has been conducted to apply additional variables and various methodologies other than financial information to predict corporate bankruptcy. It has become an important research task to determine whether it has an effect. In this study, we examined the impact of electronic payment-related information, which constitutes non-financial information, when predicting the closure of business operators using electronic payment service and examined the difference in closure prediction accuracy according to the combination of financial and non-financial information. Specifically, three research models consisting of a financial information model, a non-financial information model, and a combined model were designed, and the closure prediction accuracy was confirmed with six algorithms including the Multi Layer Perceptron (MLP) algorithm. The model combining financial and non-financial information showed the highest prediction accuracy, followed by the non-financial information model and the financial information model in order. As for the prediction accuracy of business closure by algorithm, XGBoost showed the highest prediction accuracy among the six algorithms. As a result of examining the relative importance of a total of 87 variables used to predict business closure, it was confirmed that more than 70% of the top 20 variables that had a significant impact on the prediction of business closure were non-financial information. Through this, it was confirmed that electronic payment-related information of non-financial information is an important variable in predicting business closure, and the possibility of using non-financial information as an alternative to financial information was also examined. Based on this study, the importance of collecting and utilizing non-financial information as information that can predict business closure is recognized, and a plan to utilize it for corporate decision-making is also proposed.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.287-316
• /
• 2023

As global energy crisis and the COVID-19 pandemic have emerged as social issues, there is a growing demand for companies to move away from profit-centric business models and embrace sustainable management that balances environmental, social, and governance (ESG) factors. ESG activities of companies vary across industries, and industry-specific weights are applied in ESG evaluations. Therefore, it is important to develop strategic management approaches that reflect the characteristics of each industry and the importance of each ESG factor. Additionally, with the stance of strengthened focus on ESG disclosures, specific guidelines are needed to identify and report on sustainable management activities of domestic companies. To understand corporate sustainability strategies, analyzing ESG reports and news articles by industry can help identify strategic characteristics in specific industries. However, each company has its own unique strategies and report structures, making it difficult to grasp detailed trends or action items. In our study, we analyzed ESG reports (2019-2021) and news articles (2019-2022) of six companies in the 'Finance,' 'Manufacturing,' and 'IT' sectors to examine the sustainability strategies of leading domestic ESG companies. Text mining techniques such as keyword frequency analysis and topic modeling were applied to identify industry-specific, ESG element-specific management strategies and issues. The analysis revealed that in the 'Finance' sector, customer-centric management strategies and efforts to promote an inclusive culture within and outside the company were prominent. Strategies addressing climate change, such as carbon neutrality and expanding green finance, were also emphasized. In the 'Manufacturing' sector, the focus was on creating sustainable communities through occupational health and safety issues, sustainable supply chain management, low-carbon technology development, and eco-friendly investments to achieve carbon neutrality. In the 'IT' sector, there was a tendency to focus on technological innovation and digital responsibility to enhance social value through technology. Furthermore, the key issues identified in the ESG factors were as follows: under the 'Environmental' element, issues such as greenhouse gas and carbon emission management, industry-specific eco-friendly activities, and green partnerships were identified. Under the 'Social' element, key issues included social contribution activities through stakeholder engagement, supporting the growth and coexistence of members and partner companies, and enhancing customer value through stable service provision. Under the 'Governance' element, key issues were identified as strengthening board independence through the appointment of outside directors, risk management and communication for sustainable growth, and establishing transparent governance structures. The exploration of the relationship between ESG disclosures in reports and ESG issues in news articles revealed that the sustainability strategies disclosed in reports were aligned with the issues related to ESG disclosed in news articles. However, there was a tendency to strengthen ESG activities for prevention and improvement after negative media coverage that could have a negative impact on corporate image. Additionally, environmental issues were mentioned more frequently in news articles compared to ESG reports, with environmental-related keywords being emphasized in the 'Finance' sector in the reports. Thus, ESG reports and news articles shared some similarities in content due to the sharing of information sources. However, the impact of media coverage influenced the emphasis on specific sustainability strategies, and the extent of mentioning environmental issues varied across documents. Based on our study, the following contributions were derived. From a practical perspective, companies need to consider their characteristics and establish sustainability strategies that align with their capabilities and situations. From an academic perspective, unlike previous studies on ESG strategies, we present a subdivided methodology through analysis considering the industry-specific characteristics of companies.

• The Mathematical Education
• /
• v.62 no.3
• /
• pp.435-455
• /
• 2023

This study primarily focused on the development of an Explainable Artificial Intelligence (XAI) model to discern and analyze papers with significant impact in the field of mathematics education. To achieve this, meta-information from 29 domestic and international mathematics education journals was utilized to construct a comprehensive academic research network in mathematics education. This academic network was built by integrating five sub-networks: 'paper and its citation network', 'paper and author network', 'paper and journal network', 'co-authorship network', and 'author and affiliation network'. The Random Forest machine learning model was employed to evaluate the impact of individual papers within the mathematics education research network. The SHAP, an XAI model, was used to analyze the reasons behind the AI's assessment of impactful papers. Key features identified for determining impactful papers in the field of mathematics education through the XAI included 'paper network PageRank', 'changes in citations per paper', 'total citations', 'changes in the author's h-index', and 'citations per paper of the journal'. It became evident that papers, authors, and journals play significant roles when evaluating individual papers. When analyzing and comparing domestic and international mathematics education research, variations in these discernment patterns were observed. Notably, the significance of 'co-authorship network PageRank' was emphasized in domestic mathematics education research. The XAI model proposed in this study serves as a tool for determining the impact of papers using AI, providing researchers with strategic direction when writing papers. For instance, expanding the paper network, presenting at academic conferences, and activating the author network through co-authorship were identified as major elements enhancing the impact of a paper. Based on these findings, researchers can have a clear understanding of how their work is perceived and evaluated in academia and identify the key factors influencing these evaluations. This study offers a novel approach to evaluating the impact of mathematics education papers using an explainable AI model, traditionally a process that consumed significant time and resources. This approach not only presents a new paradigm that can be applied to evaluations in various academic fields beyond mathematics education but also is expected to substantially enhance the efficiency and effectiveness of research activities.

• Journal of Service Research and Studies
• /
• v.13 no.2
• /
• pp.114-129
• /
• 2023

In the era of the 4th industrial revolution, the importance of the 4th industrial revolution technology is increasing in the service industry. The purpose of this study is to identify the development and utilization status of the 4th industrial revolution technology in the service industry and to derive the characteristics and implications of the 4th industrial revolution technology innovation in the service industry. In this study, research and analysis were conducted based on the business activity survey data in order to identify the technological innovation characteristics of the 4th industrial revolution in the service industry. The 4th industrial revolution technology in the service industry was analyzed in terms of company ratio, technology development and utilization rate, development/utilization technology, technology application field, and technology development method. In addition, the trend of the 4th industrial revolution technology change in the service industry was also analyzed. The 4th industrial revolution technology utilization and development status of other industries was compared and analyzed. In particular, the service industry 4th industrial revolution technology innovation type was divided into 4 types from the perspective of the 4th industrial revolution company ratio and the 4th industrial revolution company ratio growth rate, and types for each service industry were derived. The characteristics and implications of the 4th industrial revolution technology innovation in the service industry were presented from nine perspectives. As a result of the study, it was found that companies in the service industry were developing or using 4th industrial revolution technologies more actively than companies in other industries, and it was analyzed that the gap was further widening. By service industry, information and communication, finance and insurance, and educational service showed relatively high rates of developing or utilizing 4th industrial revolution technologies. The service industries in which the share of 4th industrial revolution companies increased the most were real estate, education service, health and social welfare service. In particular, cloud, big data, and artificial intelligence were analyzed as the three core technologies of the fourth industrial revolution. The service industry can be classified into 4 types in terms of the 4th industrial revolution company ratio and growth rate, and service industry innovation measures that reflect the differentiated innovation characteristics of each type are needed.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.263-286
• /
• 2022

This study acquires NBA statistical information for a total of 32 years from 1990 to 2022 using web crawling, observes variables of interest through exploratory data analysis, and generates related derived variables. Unused variables were removed through a purification process on the input data, and correlation analysis, t-test, and ANOVA were performed on the remaining variables. For the variable of interest, the difference in the mean between the groups that advanced to the playoffs and did not advance to the playoffs was tested, and then to compensate for this, the average difference between the three groups (higher/middle/lower) based on ranking was reconfirmed. Of the input data, only this year's season data was used as a test set, and 5-fold cross-validation was performed by dividing the training set and the validation set for model training. The overfitting problem was solved by comparing the cross-validation result and the final analysis result using the test set to confirm that there was no difference in the performance matrix. Because the quality level of the raw data is high and the statistical assumptions are satisfied, most of the models showed good results despite the small data set. This study not only predicts NBA game results or classifies whether or not to advance to the playoffs using machine learning, but also examines whether the variables of interest are included in the major variables with high importance by understanding the importance of input attribute. Through the visualization of SHAP value, it was possible to overcome the limitation that could not be interpreted only with the result of feature importance, and to compensate for the lack of consistency in the importance calculation in the process of entering/removing variables. It was found that a number of variables related to three points and errors classified as subjects of interest in this study were included in the major variables affecting advancing to the playoffs in the NBA. Although this study is similar in that it includes topics such as match results, playoffs, and championship predictions, which have been dealt with in the existing sports data analysis field, and comparatively analyzed several machine learning models for analysis, there is a difference in that the interest features are set in advance and statistically verified, so that it is compared with the machine learning analysis result. Also, it was differentiated from existing studies by presenting explanatory visualization results using SHAP, one of the XAI models.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.311-328
• /
• 2022

Because of the spread of smartphones due to the development of information and communication technology, online shopping mall services can be used on computers and mobile devices. As a result, the number of users using the online shopping mall service increases rapidly, and the types of products traded are also growing. Therefore, to maximize profits, companies need to provide information that may interest users. To this end, the recommendation system presents necessary information or products to the user based on the user's past behavioral data or behavioral purchase records. Representative overseas companies that currently provide recommendation services include Netflix, Amazon, and YouTube. These companies support users' purchase decisions by recommending products to users using ratings, purchase records, and clickstream data that users give to the items. In addition, users refer to the ratings left by other users about the product before buying a product. Most users tend to provide ratings only to products they are satisfied with, and the higher the rating, the higher the purchase intention. And recently, e-commerce sites have provided users with the ability to vote on whether product reviews are helpful. Through this, the user makes a purchase decision by referring to reviews and ratings of products judged to be beneficial. Therefore, in this study, the correlation between the product rating and the helpful information of the review is identified. The valuable data of the evaluation is reflected in the recommendation system to check the recommendation performance. In addition, we want to compare the results of skipping all the ratings in the traditional collaborative filtering technique with the recommended performance results that reflect only the 4 and 5 ratings. For this purpose, electronic product data collected from Amazon was used in this study, and the experimental results confirmed a correlation between ratings and review usefulness information. In addition, as a result of comparing the recommendation performance by reflecting all the ratings and only the 4 and 5 points in the recommendation system, the recommendation performance of remembering only the 4 and 5 points in the recommendation system was higher. In addition, as a result of reflecting review usefulness information in the recommendation system, it was confirmed that the more valuable the review, the higher the recommendation performance. Therefore, these experimental results are expected to improve the performance of personalized recommendation services in the future and provide implications for e-commerce sites.