• Journal of Dental Rehabilitation and Applied Science
• /
• v.27 no.2
• /
• pp.141-147
• /
• 2011

The aim of this study was to evaluate histomorphometrically and compare the efficiency of various bone graft material and autogenous tooth bone graft material which were used in sinus bone graft procedure. Subjects were the 24 patients who had treated with sinus bone graft using lateral approach from October 2007 to September 2009 at SNUBH. The average age was $52.51{\pm}11.86$ years. All cases was taken after 4month of procedure and divided into 3 groups according to bone graft material. Group 1: autogenous tooth bone graft material, Group 2: OrthoblastII(integra lifescience corp. Irvine, US)+Biocera(Osscotec, seoul, korea), group 3: DBX(Synthes, USA)+BioOss(Geistlich Pharm AG, Wolhusen, Switzerland). Total 37 implant placement area were included and evaluated(7 in group 1, 10 in group 2, 20 in group 3). Evaluation of new bone formation, ratio of woven bone to lamellar bone, ratio of new bone to graft material were performed on each tissue section. Kruskal-Wallis test was used for statistical analysis(SPSS Ver. 12.0, USA). New bone formation were $52.5{\pm}10.7%$ in group 1, $52.0{\pm}23.4%$ in group 2, $51.0{\pm}18.3%$ in group 3. There were no statistical significant differences between each groups. Ratio of woven bone to lamella bone were $82.8{\pm}15.3%$ in group 1, $36.7{\pm}59.3%$ in group 2, $31.0{\pm} 51.2%$ in group 3. Ratio of new bone to graft material were $81.3{\pm}10.4%$ in group 1, $72.5{\pm}28.8%$ in group 2, $80.3{\pm}24.0%$ in group 3. After 4 month of healing period, all group showed favorable new bone formation and around graft material and implant. Within limitation of our study, it is suggested that autogenous tooth bone graft material might be used as novel bone graft material for sinus bone graft.

• Asia pacific journal of information systems
• /
• v.19 no.4
• /
• pp.47-75
• /
• 2009

Recently, researches on Management Information Systems (MIS) have laid out theoretical foundation and academic paradigms by introducing diverse theories, themes, and methodologies. Especially, academic paradigms of MIS encourage a user-friendly approach by developing the technologies from the users' perspectives, which reflects the existence of strong causal relationships between information systems and user's behavior. As in other areas in social science the use of structural equation modeling (SEM) has rapidly increased in recent years especially in the MIS area. The SEM technique is important because it provides powerful ways to address key IS research problems. It also has a unique ability to simultaneously examine a series of casual relationships while analyzing multiple independent and dependent variables all at the same time. In spite of providing many benefits to the MIS researchers, there are some potential pitfalls with the analytical technique. The research objective of this study is to provide some guidelines for an appropriate use of SEM based on the assessment of current practice of using SEM in the MIS research. This study focuses on several statistical issues related to the use of SEM in the MIS research. Selected articles are assessed in three parts through the meta analysis. The first part is related to the initial specification of theoretical model of interest. The second is about data screening prior to model estimation and testing. And the last part concerns estimation and testing of theoretical models based on empirical data. This study reviewed the use of SEM in 164 empirical research articles published in four major MIS journals in Korea (APJIS, ISR, JIS and JITAM) from 1991 to 2007. APJIS, ISR, JIS and JITAM accounted for 73, 17, 58, and 16 of the total number of applications, respectively. The number of published applications has been increased over time. LISREL was the most frequently used SEM software among MIS researchers (97 studies (59.15%)), followed by AMOS (45 studies (27.44%)). In the first part, regarding issues related to the initial specification of theoretical model of interest, all of the studies have used cross-sectional data. The studies that use cross-sectional data may be able to better explain their structural model as a set of relationships. Most of SEM studies, meanwhile, have employed. confirmatory-type analysis (146 articles (89%)). For the model specification issue about model formulation, 159 (96.9%) of the studies were the full structural equation model. For only 5 researches, SEM was used for the measurement model with a set of observed variables. The average sample size for all models was 365.41, with some models retaining a sample as small as 50 and as large as 500. The second part of the issue is related to data screening prior to model estimation and testing. Data screening is important for researchers particularly in defining how they deal with missing values. Overall, discussion of data screening was reported in 118 (71.95%) of the studies while there was no study discussing evidence of multivariate normality for the models. On the third part, issues related to the estimation and testing of theoretical models on empirical data, assessing model fit is one of most important issues because it provides adequate statistical power for research models. There were multiple fit indices used in the SEM applications. The test was reported in the most of studies (146 (89%)), whereas normed-test was reported less frequently (65 studies (39.64%)). It is important that normed- of 3 or lower is required for adequate model fit. The most popular model fit indices were GFI (109 (66.46%)), AGFI (84 (51.22%)), NFI (44 (47.56%)), RMR (42 (25.61%)), CFI (59 (35.98%)), RMSEA (62 (37.80)), and NNFI (48 (29.27%)). Regarding the test of construct validity, convergent validity has been examined in 109 studies (66.46%) and discriminant validity in 98 (59.76%). 81 studies (49.39%) have reported the average variance extracted (AVE). However, there was little discussion of direct (47 (28.66%)), indirect, and total effect in the SEM models. Based on these findings, we suggest general guidelines for the use of SEM and propose some recommendations on concerning issues of latent variables models, raw data, sample size, data screening, reporting parameter estimated, model fit statistics, multivariate normality, confirmatory factor analysis, reliabilities and the decomposition of effects.

• Journal of the Korea Institute of Building Construction
• /
• v.24 no.2
• /
• pp.273-284
• /
• 2024

This study investigates the impact of international oil price fluctuations on overseas construction orders secured by domestic and foreign companies. The analysis employs statistical data spanning the past 20 years, encompassing international oil prices, overseas construction orders from domestic firms, and new overseas construction orders from the top 250 global construction companies. The correlation between these variables is assessed using correlation coefficients(R), determination coefficients(R²), and p-values. The results indicate a strong positive correlation between international oil prices and overseas construction orders. The correlation coefficient between domestic overseas construction orders and oil prices is found to be 0.8 or higher, signifying a significant influence. Similarly, a high correlation coefficient of 0.76 is observed between oil prices and new orders from leading global construction companies. Further analysis reveals a particularly strong correlation between oil prices and overseas construction orders in Asia and the Middle East, potentially due to the prevalence of oil-related projects in these regions. Additionally, a high correlation is observed between oil prices and orders for industrial facilities compared to architectural projects. This suggests an increase in plant construction volumes driven by fluctuations in oil prices. Based on these findings, the study proposes an entry strategy for navigating oil price volatility and maintaining competitiveness in the overseas construction market. Key recommendations include diversifying project locations and supplier bases; utilizing hedging techniques for exchange rate risk management, adapting to local infrastructure and market conditions, establishing local partnerships and securing skilled local labor, implementing technological innovations and digitization at construction sites to enhance productivity and cost reduction The insights gained from this study, coupled with the proposed overseas expansion strategies, offer valuable guidance for mitigating risks in the global construction market and fostering resilience in response to international oil price fluctuations. This approach is expected to strengthen the competitiveness of domestic and foreign construction firms seeking success in the international arena.

• Fisheries and Aquatic Sciences
• /
• v.26 no.12
• /
• pp.738-751
• /
• 2023

The Sembilan Archipelago is famous for its great biodiversity, in which the humphead wrasse (Cheilinus undulatus) (locally named Napoleon fish) is the primary commodity (economically important), and currently, the environmental degradation occurs due to anthropogenic activities. This study aimed to examine the eco-environmental parameters and assess their influence on the abundance of humphead wrasse and other coral reef fish compositions in the Sembilan Archipelago. Direct field monitoring was performed using a visual census throughout an approximately one km transect. Coral cover data collection and assessment were also carried out. A coastal water quality index (CWQI) was used to assess the water quality status. Furthermore, statistical-based analyses [hierarchical clustering, Pearson's correlation, principal component analysis (PCA), and canonical correspondence analysis (CCA)] were performed to examine the correlation between eco-environmental parameters. The Napoleon fish was only found at stations 1 and 2, with a density of about 3.8 Ind/ha, aligning with the dominant composition of the family Serranidae (covering more than 15% of the total community) and coinciding with the higher coral mortality and lower reef fish abundance. The coral reef conditions were generally ideal for supporting marine life, with a living coral percentage of about > 50% in all stations. Based on CWQI, the study area is categorized as good and excellent water quality. Of the 60 parameter values examined, the phytoplankton abundance, Napoleon fish, and temperature are highly correlated, with a correlation coefficient value greater than 0.7, and statistically significant (F < 0.05). Although the adaptation of reef fish to water quality parameters varies greatly, the most influential parameters in shaping their composition in the study area are living corals, nitrites, ammonia, larval abundance, and temperature.

• Journal of Korean Academy of Nursing
• /
• v.13 no.1
• /
• pp.7-21
• /
• 1983

For the flexible and rational distribution of limited existing health resources based on measurements of individual risk, the socalled Risk Approach is being proposed by the World Health Organization as a managerial tool in maternal and child health care program. This approach, in principle, puts us under the necessity of developing a technique by which we will be able to measure the degree of risk or to discriminate the future outcomes of pregnancy on the basis of prior information obtainable at prenatal care delivery settings. Numerous recent studies have focussed on the identification of relevant risk factors as the Prior infer mation and on defining the adverse outcomes of pregnancy to be dicriminated, and also have tried on how to develope scoring system of risk factors for the quantitative assessment of the factors as the determinant of pregnancy outcomes. Once the scoring system is established the technique of classifying the patients into with normal and with adverse outcomes will be easily de veloped. The scoring system should be developed to meet the following four basic requirements. 1) Easy to construct 2) Easy to use 3) To be theoretically sound 4) To be valid In searching for a feasible methodology which will meet these requirements, the author has attempted to apply the“Likelihood Method”, one of the well known principles in statistical analysis, to develop such scoring system according to the process as follows. Step 1. Classify the patients into four groups: Group $A_1$: With adverse outcomes on fetal (neonatal) side only. Group $A_2$: With adverse outcomes on maternal side only. Group $A_3$: With adverse outcome on both maternal and fetal (neonatal) sides. Group B: With normal outcomes. Step 2. Construct the marginal tabulation on the distribution of risk factors for each group. Step 3. For the calculation of risk score, take logarithmic transformation of relative proport-ions of the distribution and round them off to integers. Step 4. Test the validity of the score chart. h total of 2, 282 maternity records registered during the period of January 1, 1982-December 31, 1982 at Ewha Womans University Hospital were used for this study and the“Questionnaire for Maternity Record for Prenatal and Intrapartum High Risk Screening”developed by the Korean Institute for Population and Health was used to rearrange the information on the records into an easy analytic form. The findings of the study are summarized as follows. 1) The risk score chart constructed on the basis of“Likelihood Method”ispresented in Table 4 in the main text. 2) From the analysis of the risk score chart it was observed that a total of 24 risk factors could be identified as having significant predicting power for the discrimination of pregnancy outcomes into four groups as defined above. They are: (1) age (2) marital status (3) age at first pregnancy (4) medical insurance (5) number of pregnancies (6) history of Cesarean sections (7). number of living child (8) history of premature infants (9) history of over weighted new born (10) history of congenital anomalies (11) history of multiple pregnancies (12) history of abnormal presentation (13) history of obstetric abnormalities (14) past illness (15) hemoglobin level (16) blood pressure (17) heart status (18) general appearance (19) edema status (20) result of abdominal examination (21) cervix status (22) pelvis status (23) chief complaints (24) Reasons for examination 3) The validity of the score chart turned out to be as follows: a) Sensitivity: Group $A_1$: 0.75 Group $A_2$: 0.78 Group $A_3$: 0.92 All combined : 0.85 b) Specificity : 0.68 4) The diagnosabilities of the“score chart”for a set of hypothetical prevalence of adverse outcomes were calculated as follows (the sensitivity“for all combined”was used). Hypothetidal Prevalence : 5％ 10％ 20％ 30％ 40％ 50％ 60％ Diagnosability : 12% 23% 40% 53% 64% 75% 80%.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.6
• /
• pp.2465-2472
• /
• 2014

Background: The American Joint Committee on Cancer (AJCC) published a new staging system ($7^{th}$ edition) in 2009. In our study, we evaluated the survival results and prognostic factors among T4 local advanced non-small cell lung cancer (LA-NSCLC) patients in a large heterogeneous group, in accordance with this new system. Materials and Methods: We retrospectively evaluated the files of 122 T4 N0-3 M0 LA-NSCLC patients, identified according to the new staging system, treated at two centers between November 2003 and June 2012. Variables correlating with univariate survival at p<0.20 were later included in multivariate Cox regression analysis. Here, selection of relevant predictors of survival was carried out in accordance with the likelihood ratio formula with p<0.05 regarded as significant. Results: The median age was 60 and the median follow-up period was 17.4 months. Median overall survival (OS) was 18.3 months, the 1 year overall survival (OS) rate was 72%, and the 5 year OS rate was 28%. Statistically significant predictors of survival were (p<0.20) ECOG-PS (Eastern Cooperative Oncology Group Performance Status), age, T4 factor subgroup, stage and primary treatment in OS univariate analysis. On multivariate analysis for OS ECOG-PS (p=0.001), diagnostic stage (p=0.021), and primary treatment (p=0.004) were significant. In the group receiving non-curative treatment, the median OS was 11.0 months, while it was 19.0 months in the definitive RT group and 26.6 months in the curative treatment group. There was a significant difference between the non-curative group and the groups which had definitive RT and curative operations (respectively p<0.001 and p=0.001) in terms of OS, but not between the groups which had definitive RT and curative operations. The median event free survival (EFS) rate was 9.9 months, with rates of 46% and 19% at 3 and 5 years, respectively. On univariate analysis of EFS rate with ECOG-PS, weight loss and staging, statistical significance was found only for thorax computerized tomography (CT)+18F-fluorodeoxy-glucose positron emission tomography-CT (PET-CT) use, stage and primary treatment (p<0.20). In multivariate analysis with EFS, only the primary treatment was statistically significant (p=0.001). In the group receiving non-curative treatment, the median EFS was 10.5 months while in the curative operation group it was 14.7 months. When all the primary treatment groups were taken into consideration, grade III/IV side effect swas observed in 57 patients (46.6%). Esophagitis was most prominent among those that received definitive radiotherapy. Conclusions: Independent prognostic factors among these 122 heterogeneous LA-NSCLC T4 N0-3 M0 patients were age at diagnosis, ECOG-PS, stage and primary treatment, the last also being a significant prognostic indicator of EFS. Our findings point to the importance of appropriate staging and a multidisciplinary approach with modern imaging methods in this patient group. In those with T4 lesions, treatment selection and the effective use of curative potential should be the most important goal of clinical care.

• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.93-107
• /
• 2014

In this paper, we report what we have observed with regard to user-perspective issue clustering based on multi-layered two-mode network analysis. This work is significant in the context of data collection by companies about customer needs. Most companies have failed to uncover such needs for products or services properly in terms of demographic data such as age, income levels, and purchase history. Because of excessive reliance on limited internal data, most recommendation systems do not provide decision makers with appropriate business information for current business circumstances. However, part of the problem is the increasing regulation of personal data gathering and privacy. This makes demographic or transaction data collection more difficult, and is a significant hurdle for traditional recommendation approaches because these systems demand a great deal of personal data or transaction logs. Our motivation for presenting this paper to academia is our strong belief, and evidence, that most customers' requirements for products can be effectively and efficiently analyzed from unstructured textual data such as Internet news text. In order to derive users' requirements from textual data obtained online, the proposed approach in this paper attempts to construct double two-mode networks, such as a user-news network and news-issue network, and to integrate these into one quasi-network as the input for issue clustering. One of the contributions of this research is the development of a methodology utilizing enormous amounts of unstructured textual data for user-oriented issue clustering by leveraging existing text mining and social network analysis. In order to build multi-layered two-mode networks of news logs, we need some tools such as text mining and topic analysis. We used not only SAS Enterprise Miner 12.1, which provides a text miner module and cluster module for textual data analysis, but also NetMiner 4 for network visualization and analysis. Our approach for user-perspective issue clustering is composed of six main phases: crawling, topic analysis, access pattern analysis, network merging, network conversion, and clustering. In the first phase, we collect visit logs for news sites by crawler. After gathering unstructured news article data, the topic analysis phase extracts issues from each news article in order to build an article-news network. For simplicity, 100 topics are extracted from 13,652 articles. In the third phase, a user-article network is constructed with access patterns derived from web transaction logs. The double two-mode networks are then merged into a quasi-network of user-issue. Finally, in the user-oriented issue-clustering phase, we classify issues through structural equivalence, and compare these with the clustering results from statistical tools and network analysis. An experiment with a large dataset was performed to build a multi-layer two-mode network. After that, we compared the results of issue clustering from SAS with that of network analysis. The experimental dataset was from a web site ranking site, and the biggest portal site in Korea. The sample dataset contains 150 million transaction logs and 13,652 news articles of 5,000 panels over one year. User-article and article-issue networks are constructed and merged into a user-issue quasi-network using Netminer. Our issue-clustering results applied the Partitioning Around Medoids (PAM) algorithm and Multidimensional Scaling (MDS), and are consistent with the results from SAS clustering. In spite of extensive efforts to provide user information with recommendation systems, most projects are successful only when companies have sufficient data about users and transactions. Our proposed methodology, user-perspective issue clustering, can provide practical support to decision-making in companies because it enhances user-related data from unstructured textual data. To overcome the problem of insufficient data from traditional approaches, our methodology infers customers' real interests by utilizing web transaction logs. In addition, we suggest topic analysis and issue clustering as a practical means of issue identification.

• Korean Journal of Psychosomatic Medicine
• /
• v.24 no.1
• /
• pp.66-73
• /
• 2016

Objectives : The purpose of this study was to investigate the characteristics of psychosocial factors related to functional dyspepsia(FD) and their effects on quality of life(QOL) in firefighters. Methods : This study examined data collected from 1,217 firefighters. We measured psychological symptoms by Patient Health Questionnaire-9(PHQ-9), Generalized Anxiety Disorder questionnaire(GAD-7), Korean Occupational Stress Scale(KOSS), Ways of Coping checklist(WCCL), Rosenberg's Self-Esteem Scale(RSES) and World Health Organization Quality of Life Scale abbreviated version(WHOQOL-BREF). Chi-square test, independent t-test, Pearson's correlation test, logistic regression analysis, and hierarchical regression analysis were used as statistical analysis methods. Results : For the group with FD, the male participants showed significantly higher frequency(p=0.006) compared to the female participants. The group with FD had higher scores for depressive symptoms(p<.001), anxiety (p<.001), and occupational stress(p<.001), and did lower scores for self-esteem(p=.008), quality of life(p<.001) than those without FD. The FD risk was higher in the following KOSS subcategories: job demand(OR 1.94, 95% CI : 1.29-2.93), lack of reward(OR 2.47, 95% CI : 1.61-3.81), and occupational climate(OR 1.51, 95% CI : 1.01-2.24). In the hierarchical regression analysis, QOL was best predicted by depressive symptoms, self-esteem, and occupational stress. Three predictive variables above accounts for 42.0% variance explained of total variance. Conclusions : The psychosocial factors showed significant effects on FD, and predictive variables for QOL were identified based on regression analysis. The results suggest that the psychiatric approach should be accompanied with medical approach in future FD assessment.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.1-17
• /
• 2019

Because stock price forecasting is an important issue both academically and practically, research in stock price prediction has been actively conducted. The stock price forecasting research is classified into using structured data and using unstructured data. With structured data such as historical stock price and financial statements, past studies usually used technical analysis approach and fundamental analysis. In the big data era, the amount of information has rapidly increased, and the artificial intelligence methodology that can find meaning by quantifying string information, which is an unstructured data that takes up a large amount of information, has developed rapidly. With these developments, many attempts with unstructured data are being made to predict stock prices through online news by applying text mining to stock price forecasts. The stock price prediction methodology adopted in many papers is to forecast stock prices with the news of the target companies to be forecasted. However, according to previous research, not only news of a target company affects its stock price, but news of companies that are related to the company can also affect the stock price. However, finding a highly relevant company is not easy because of the market-wide impact and random signs. Thus, existing studies have found highly relevant companies based primarily on pre-determined international industry classification standards. However, according to recent research, global industry classification standard has different homogeneity within the sectors, and it leads to a limitation that forecasting stock prices by taking them all together without considering only relevant companies can adversely affect predictive performance. To overcome the limitation, we first used random matrix theory with text mining for stock prediction. Wherever the dimension of data is large, the classical limit theorems are no longer suitable, because the statistical efficiency will be reduced. Therefore, a simple correlation analysis in the financial market does not mean the true correlation. To solve the issue, we adopt random matrix theory, which is mainly used in econophysics, to remove market-wide effects and random signals and find a true correlation between companies. With the true correlation, we perform cluster analysis to find relevant companies. Also, based on the clustering analysis, we used multiple kernel learning algorithm, which is an ensemble of support vector machine to incorporate the effects of the target firm and its relevant firms simultaneously. Each kernel was assigned to predict stock prices with features of financial news of the target firm and its relevant firms. The results of this study are as follows. The results of this paper are as follows. (1) Following the existing research flow, we confirmed that it is an effective way to forecast stock prices using news from relevant companies. (2) When looking for a relevant company, looking for it in the wrong way can lower AI prediction performance. (3) The proposed approach with random matrix theory shows better performance than previous studies if cluster analysis is performed based on the true correlation by removing market-wide effects and random signals. The contribution of this study is as follows. First, this study shows that random matrix theory, which is used mainly in economic physics, can be combined with artificial intelligence to produce good methodologies. This suggests that it is important not only to develop AI algorithms but also to adopt physics theory. This extends the existing research that presented the methodology by integrating artificial intelligence with complex system theory through transfer entropy. Second, this study stressed that finding the right companies in the stock market is an important issue. This suggests that it is not only important to study artificial intelligence algorithms, but how to theoretically adjust the input values. Third, we confirmed that firms classified as Global Industrial Classification Standard (GICS) might have low relevance and suggested it is necessary to theoretically define the relevance rather than simply finding it in the GICS.