• Information Systems Review
• /
• v.18 no.4
• /
• pp.17-42
• /
• 2016

Information security incidents caused by authorized insiders are increasing in financial firms, and this increase is particularly increased by outsourced contractors. With the increase in outsourcing in financial firms, outsourced contractors having authorized right has become a threat and could violate an organization's information security policy. This study aims to analyze the differences between own employees and outsourced contractors and to determine the factors affecting the violation of information security policy to mitigate information security incidents. This study examines the factors driving employees to violate information security policy in financial firms based on the theory of planned behavior, general deterrence theory, and information security awareness, and the moderating effects of employee type between own employees and outsourced contractors. We used 363 samples that were collected through both online and offline surveys and conducted partial least square-structural equation modeling and multiple group analysis to determine the differences between own employees (246 samples, 68%) and outsourced contractors (117 samples, 32%). We found that the perceived sanction and information security awareness support the information security policy violation attitude and subjective norm, and the perceived sanction does not support the information security policy behavior control. The moderating effects of employee type in the research model were also supported. According to the t-test result between own employees and outsourced contractors, outsourced contractors' behavior control supported information security violation intention but not subject norms. The academic implications of this study is expected to be the basis for future research on outsourced contractors' violation of information security policy and a guide to develop information security awareness programs for outsourced contractors to control these incidents. Financial firms need to develop an information security awareness program for outsourced contractors to increase the knowledge and understanding of information security policy. Moreover, this program is effective for outsourced contractors.

• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.203-212
• /
• 2024

The purpose of this study was to survey by the veterinary hospital Specialists (VHSs) and radiology students (RSs) for radiology curriculum development veterinary hospital (VH), and for veterinary hospital radiological technologists (VHRTs). VHSs were surveyed to regarding the basic information and radiological examination training, radiological examination experience, anatomy physiology, radiation safety management training, radiation biology training. RSs were surveyed to regarding the basic information and career paths, VH awareness, and VH-related department environments. The survey results were quantitatively entered into Excel and then analyzed using the SPSS ver. 26.0. The students were aged by 22.6 years old, and out of 171 students, male and female were 92 and 79 espectively. In employment career paths, 62.6% of all subjects responded that employment prospects at medical institutions were good. Employment prospects outside of medical institutions, VH had the highest number of students. Of the 83 students who responded that they wanted to work at a VH, 64 students liked animals, and 47 students the high potential for advancement. Of the 159 students who responded that there is potential for development of VH, 96.2% responded that it was due to the increase in companion animals. In the VH-related department environment, 94.7% responded that there was no related equipment, and 72.5% responded that the department needed to open animal care courses and 82.5% anatomy and physiology courses. 76.6% responded that they would be willing to take animal-related courses if they were offered. Among the 20 VHSAs, 4 had no experience in radiological examination of animals, 2 VHRTs, and 2 others. There were 7 people who had not received training in animal radiography, and 2 VHRTs had not received training in animal care and animal anatomy and physiology. This study is expected to be helpful in developing a radiology curriculum for VHRTs in the future.

• Journal of agricultural medicine and community health
• /
• v.27 no.2
• /
• pp.87-105
• /
• 2002

In order to find out the knowledge, attitude, and experience of community health practitioners(CHP) on complementary therapy, 393 community health practitioners who provide primary health care service in Busan, Kyeongnam, and Daegu, Gyeongbuk regions were interviewed or surveyed by mail from February 1st to March 31st, 2002. In terms of interest of CHPs toward 11 different hinds of complementary therapy, the rate of interest for soojichim was the highest with 75.3%. Aroma therapy had the interest of 71.0% of the CHPs, oriental medicine had 67.4%, and massage had 67.4%. The interest for shiatsu was 64.6%, while homeopath had the lowest rate of interest of 18.1%. In terms of reliance on the treatment results, oriental medicine scored the highest with 92.6%, and soojichim, massage, and shiatsu followed with 85.5%, 83.7%, and 81.7% respectively. Homeopath had the lowest reliance of 18.1%. The 65.1% of the CHPs had the experience of recommending oriental medicine to patients. 50.4% indicated that they had recommended soojichim, and 44.8% had recommended massage before. Shiatsu and aromatherapy followed with 34.4% and Homeopath had the lowest rate of 2.80%. When CHPs were asked if they had received any training in complementary therapy, 33.1% indicated that they had studied soojichim and 13.2%stated that they had learned oriental medicine. Aromatherapy, massage, and shiatsu followed with 11.2%, 8.4%, and 5.6% respectively On the other hand, none of the CHPs had received training in homeopath. In terms of using complementary therapy during the past 5 years, 23.9% had been treated with oriental medicine, and 18.896 had received soojichim. 5.9% had received aromatherapy, 5.3% had used massage, and 5.1% had experience with shiatsu. None of the practitioners had used homeopath during the past 5 years. Significantly many number of practitioners indicated that they had excellent treatment results with all hinds of complementary therapy, and there were rare cares of side effects. When they were asked if they wanted complementary therapy to become part of the curriculum during re-training or training for public service personnels, 78100 wanted soojichim, 69.2% wanted oriental medicine, and 67.9% wanted aroma therapy. 63.9% wanted shiatsu to be included, and 63.1% wanted massage. When CHPs were asked if they wanted to use complementary therapy during primary health care, 63.6% wanted to use soojichim, 52.9% wanted massage, and 51.9% wanted to use aroma therapy. Oriental medicine also showed a high rate of 50.1%. On the other hand, only a small percentage wanted to use chiropractic or homeopath with 17.0% and 12,2% respectively. Among the CHPs, there were some who had administered complementary therapy during the past 5 years. 84% had administered soojichim, 4.6% had administered oriental medicine, and 2.5% had administered massage 2.5% of the CHPs answered that they had administered aromatherapy. However, none of them had administered apitherapy or homeopath. Most of patients showed positive responses, and the rate of side effect was very low. As shown in the above results, although CHPs have a high rate of interest, reliance, and experience in recommending complementary therapy, only a low percentage of them had received any training in complementary therapy. In addition, since there were little side effects when they received or administered complementary therapy, they hoped complementary therapy, which can be beneficial to health, to be introduced to the curriculum. Therefore, in order to provide community members with complementary therapy and the correct information regarding the selection of complementary therapy that could be beneficial to health, a policy of continuous interest and support is needed so that CHPs can he provided with a systemic and rational curriculum of complementary therapy.

• Pediatric Infection and Vaccine
• /
• v.11 no.1
• /
• pp.81-89
• /
• 2004

Purpose : Retropharyngeal and parapharyngeal abscesses are often distinguishable from other head and neck abscesses on clinical grounds, but these infections can combine and the presentations are similar to one another. Because of the advances of antibiotic therapy, the frequency of the diseases decreased considerably, but recently the incidence of neck abscesses has increased. We sought to describe the clinical presentation of patients with deep neck abscess, and implications on management. Methods : For 10 year periods, 94 cases of charts were reviewed retrospectively, who were diagnosed as neck abscesses aged below 16 years old(between January 1993 to August 2003) in 4 hospitals. Deep neck abscesses were diagnosed by surgical pus drainage, neck CT (homogenous, hypodense area with ring enhancement) and neck sono findings. Results : The annual incidence of deep neck abscess has been increased since 2000. The median age of the patients was 4 years(range, 26 days~15 years); 63% of the patients were younger than 5 years. Abscesses in the submandibular space(34%) were most common, followed by peritonsillar space(29.7%), retropharyngeal space(11.7%), combined(10.8%), parotid space(7.4%) and parapharyngeal space(6.4%). Fever(73.4%), sore throat(37.2%), decreased oral intake(34%) and neck pain(27.7%) were the most common symptoms. In 6 children(6.4%), there was refusal to move neck, in 6(6.4%) headache, and in 4(4.3%) torticollis. Respiratory distress was observed in only 1 patient(2.1%) and stridor in 1 other(2.1%). The most common physical examinations were neck swelling/mass(67%), pharyngitis(46.8%), tonsillitis(36.2 %), and cervical lymphadenopathy(28.7%). Neck stiffness was observed in 4 patients(4.3%). Total 35 organisms were isolated in 33 patients. The most common organisms cultured by patients' blood or pus were S. aureus(34%) and S. pyogenes(28.6%). Most organisms were gram positive, and had sensitivities in vancomycin(96.4%), cefotaxime(88.9%), cephalothin (86.4%), trimethoprime-sulfamethoxazole(83.3%), and clindamycin(77.8%). 77 patients(81.9%) underwent surgery plus antibiotics; 17 patients(18.1%) were treated with antibiotics only. There is no significant differences between two groups. In duration of admission, fever after admission, and antibiotic treatment. Conclusion : The incidence of deep neck abscess has increased recently and the major symptoms have been changed. The incidence of respiratory distress or stridor is decreasing, while the incidence of abnormal head and neck symptoms and signs like headache, neck stiffness, refusal to move neck, or torticollis are increasing. Gram positive organisms are predominant, S. aureus is the most common followed by S. pyogenes. 1st generation cephalosporin has high sensitivity on gram positive organisms. Treatment with surgery plus antibiotics dose not significantly decrease total duration of antibiotic treatment or admission compared to treatment with antibiotics alone.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.93-111
• /
• 2013

As Internet and information technology (IT) continues to develop and evolve, the issue of big data has emerged at the foreground of scholarly and industrial attention. Big data is generally defined as data that exceed the range that can be collected, stored, managed and analyzed by existing conventional information systems and it also refers to the new technologies designed to effectively extract values from such data. With the widespread dissemination of IT systems, continual efforts have been made in various fields of industry such as R&D, manufacturing, and finance to collect and analyze immense quantities of data in order to extract meaningful information and to use this information to solve various problems. Since IT has converged with various industries in many aspects, digital data are now being generated at a remarkably accelerating rate while developments in state-of-the-art technology have led to continual enhancements in system performance. The types of big data that are currently receiving the most attention include information available within companies, such as information on consumer characteristics, information on purchase records, logistics information and log information indicating the usage of products and services by consumers, as well as information accumulated outside companies, such as information on the web search traffic of online users, social network information, and patent information. Among these various types of big data, web searches performed by online users constitute one of the most effective and important sources of information for marketing purposes because consumers search for information on the internet in order to make efficient and rational choices. Recently, Google has provided public access to its information on the web search traffic of online users through a service named Google Trends. Research that uses this web search traffic information to analyze the information search behavior of online users is now receiving much attention in academia and in fields of industry. Studies using web search traffic information can be broadly classified into two fields. The first field consists of empirical demonstrations that show how web search information can be used to forecast social phenomena, the purchasing power of consumers, the outcomes of political elections, etc. The other field focuses on using web search traffic information to observe consumer behavior, identifying the attributes of a product that consumers regard as important or tracking changes on consumers' expectations, for example, but relatively less research has been completed in this field. In particular, to the extent of our knowledge, hardly any studies related to brands have yet attempted to use web search traffic information to analyze the factors that influence consumers' purchasing activities. This study aims to demonstrate that consumers' web search traffic information can be used to derive the relations among brands and the relations between an individual brand and product attributes. When consumers input their search words on the web, they may use a single keyword for the search, but they also often input multiple keywords to seek related information (this is referred to as simultaneous searching). A consumer performs a simultaneous search either to simultaneously compare two product brands to obtain information on their similarities and differences, or to acquire more in-depth information about a specific attribute in a specific brand. Web search traffic information shows that the quantity of simultaneous searches using certain keywords increases when the relation is closer in the consumer's mind and it will be possible to derive the relations between each of the keywords by collecting this relational data and subjecting it to network analysis. Accordingly, this study proposes a method of analyzing how brands are positioned by consumers and what relationships exist between product attributes and an individual brand, using simultaneous search traffic information. It also presents case studies demonstrating the actual application of this method, with a focus on tablets, belonging to innovative product groups.

• MISULJARYO - National Museum of Korea Art Journal
• /
• v.104
• /
• pp.40-69
• /
• 2023

This paper examines the relationship between celadon wine vessels and royal banquets by focusing on their unique forms. It explores the symbolism in their forms and designs and the changes that took place in the composition of these vessels. By examining the royal annals in Goryeosa (The History of the Goryeo Dynasty), the relation of celadon wine vessels and royal banquets is examined in terms of the number of banquets held in the respective reigns of the Goryeo kings, the number of banquets held by type, and the purpose of holding them. A royal banquet was a means of strengthening the royal authority by reinforcing the hierarchy and building bonds between the king and his vassals. It was also an act of ruling that demonstrated the king's authority and power through praise of his achievements and virtues. Royal banquets were held most often during the reigns of King Yejong (r. 1105-1122), King Uijong (r. 1146-1170), King Chungnyeol (r. 1274-1308), and King Gongmin (r. 1351-1374). Particular attention is paid here to the changes in the types and forms of celadon wine vessels that occurred starting in the reigns of King Yejong and King Chungnyeol, which is also the period in which the number of royal banquets increased and royal banquet culture evolved. The king and his subjects prayed for the king's longevity at royal banquets and celebrated peaceful reigns by drinking and performing various related acts. Thus, the visual symbolism of vessels for holding, pouring, or receiving alcohol were emphasized. Since the manner of drinking at a banquet was exchanges of pouring and receiving alcohol between the king and his subjects, the design of the ewers and cups had a significant visual impact on attendees. It can be seen, therefore, that decorating wine vessels with Daoist motifs such as the immortals, luan (a mythological bird), turtle dragons, fish dragons, and gourd bottles or with Confucian designs like hibiscus roots was intended as a visual manifestation of the purpose of royal banquets, which was to celebrate the king and to pray for both loyalty and immortality. In particular, the Peach Offering Dance (獻仙桃) and Music for Returning to the Royal Palace (還宮樂), which correspond to the form and design of celadon wine vessels, was examined. The lyrics of the banquet music embodied wishes for the king's longevity, immortality, and eternal youth as well as for the prosperity of the royal court and a peaceful reign. These words are reflected in wine vessels such as the Celadon Taoist Figure-shaped Pitcher housed in the National Museum of Korea and the Bird Shaped Ewer with Daoist Priest in the Art Institute of Chicago. It is important to note that only Goryeo celadon wine vessels reflect this facet of royal banquet culture in their shape and design. The composition of wine vessel sets changed depending on the theme of the banquet and the types of liquor. After Goryeo Korea was incorporated into the Mongol Empire, new alcoholic beverages were introduced, resulting in changes in banquet culture such as the uses and composition of wine vessel sets. From the reign of King Chungnyeol (r. 1274-1308), which was under the authority of the Yuan imperial court, royal banquets began to be co-hosted by kings and princesses, Mongolian-style banquets like boerzhayan (孛兒扎宴) were held, and attendees donned the tall headdress called gugu worn by Mongol women. During the reign of King Chungnyeol, the banquet culture changed 132 banquets were held. This implies that the court tried to strengthen its authority by royal marriage with the Yuan court, which augmented the number of banquets. At these banquets, new alcoholic drinks were introduced such as grape wine, dongnak (湩酪), and distilled liquor. New wine vessels included stem cups, pear-shaped bottles (yuhuchunping), yi (匜), and cups with a dragon head. The new celadon wine vessels were all modeled after metal wares that were used in the Yuan court or in the Khanates. The changes in the celadon wine vessels of the late Goryeo era were examined here in a more specific manner than in previous studies by expanding the samples for the study to the Eurasian khanates. With the influx of new types of wine vessels, it was natural for the sets and uses of Goryeo celadon wine vessels to change in response. The new styles of celadon wine vessels linked the Goryeo court with the distant Khanates of the Mongol Empire. This paper is the beginning of a new study that examines the uses of Goryeo celadon by illuminating the relations between royal banquets and these unique celadon wine vessels that are stylistically different from everyday vessels. It is to be hoped that more studies will be conducted from diverse perspectives exploring both the usage of Goryeo celadon vessels and their users.

• Journal of Intelligence and Information Systems
• /
• v.21 no.4
• /
• pp.17-35
• /
• 2015

Demand forecasting is the activity of estimating the quantity of a product or service that consumers will purchase for a certain period of time. Developing precise forecasting models are considered important since corporates can make strategic decisions on new markets based on future demand estimated by the models. Many studies have developed market growth curve models, such as Bass, Logistic, Gompertz models, which estimate future demand when a market is in its early stage. Among the models, Bass model, which explains the demand from two types of adopters, innovators and imitators, has been widely used in forecasting. Such models require sufficient demand observations to ensure qualified results. In the beginning of a new market, however, observations are not sufficient for the models to precisely estimate the market's future demand. For this reason, as an alternative, demands guessed from those of most adjacent markets are often used as references in such cases. Reference markets can be those whose products are developed with the same categorical technologies. A market's demand may be expected to have the similar pattern with that of a reference market in case the adoption pattern of a product in the market is determined mainly by the technology related to the product. However, such processes may not always ensure pleasing results because the similarity between markets depends on intuition and/or experience. There are two major drawbacks that human experts cannot effectively handle in this approach. One is the abundance of candidate reference markets to consider, and the other is the difficulty in calculating the similarity between markets. First, there can be too many markets to consider in selecting reference markets. Mostly, markets in the same category in an industrial hierarchy can be reference markets because they are usually based on the similar technologies. However, markets can be classified into different categories even if they are based on the same generic technologies. Therefore, markets in other categories also need to be considered as potential candidates. Next, even domain experts cannot consistently calculate the similarity between markets with their own qualitative standards. The inconsistency implies missing adjacent reference markets, which may lead to the imprecise estimation of future demand. Even though there are no missing reference markets, the new market's parameters can be hardly estimated from the reference markets without quantitative standards. For this reason, this study proposes a case-based expert system that helps experts overcome the drawbacks in discovering referential markets. First, this study proposes the use of Euclidean distance measure to calculate the similarity between markets. Based on their similarities, markets are grouped into clusters. Then, missing markets with the characteristics of the cluster are searched for. Potential candidate reference markets are extracted and recommended to users. After the iteration of these steps, definite reference markets are determined according to the user's selection among those candidates. Then, finally, the new market's parameters are estimated from the reference markets. For this procedure, two techniques are used in the model. One is clustering data mining technique, and the other content-based filtering of recommender systems. The proposed system implemented with those techniques can determine the most adjacent markets based on whether a user accepts candidate markets. Experiments were conducted to validate the usefulness of the system with five ICT experts involved. In the experiments, the experts were given the list of 16 ICT markets whose parameters to be estimated. For each of the markets, the experts estimated its parameters of growth curve models with intuition at first, and then with the system. The comparison of the experiments results show that the estimated parameters are closer when they use the system in comparison with the results when they guessed them without the system.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.53-69
• /
• 2011

Vision and voice-based technologies are commonly utilized for human-robot interaction. But it is widely recognized that the performance of vision and voice-based interaction systems is deteriorated by a large margin in the real-world situations due to environmental and user variances. Human users need to be very cooperative to get reasonable performance, which significantly limits the usability of the vision and voice-based human-robot interaction technologies. As a result, touch screens are still the major medium of human-robot interaction for the real-world applications. To empower the usability of robots for various services, alternative interaction technologies should be developed to complement the problems of vision and voice-based technologies. In this paper, we propose the use of accelerometer-based gesture interface as one of the alternative technologies, because accelerometers are effective in detecting the movements of human body, while their performance is not limited by environmental contexts such as lighting conditions or camera's field-of-view. Moreover, accelerometers are widely available nowadays in many mobile devices. We tackle the problem of classifying acceleration signal patterns of 26 English alphabets, which is one of the essential repertoires for the realization of education services based on robots. Recognizing 26 English handwriting patterns based on accelerometers is a very difficult task to take over because of its large scale of pattern classes and the complexity of each pattern. The most difficult problem that has been undertaken which is similar to our problem was recognizing acceleration signal patterns of 10 handwritten digits. Most previous studies dealt with pattern sets of 8~10 simple and easily distinguishable gestures that are useful for controlling home appliances, computer applications, robots etc. Good features are essential for the success of pattern recognition. To promote the discriminative power upon complex English alphabet patterns, we extracted 'motion trajectories' out of input acceleration signal and used them as the main feature. Investigative experiments showed that classifiers based on trajectory performed 3%~5% better than those with raw features e.g. acceleration signal itself or statistical figures. To minimize the distortion of trajectories, we applied a simple but effective set of smoothing filters and band-pass filters. It is well known that acceleration patterns for the same gesture is very different among different performers. To tackle the problem, online incremental learning is applied for our system to make it adaptive to the users' distinctive motion properties. Our system is based on instance-based learning (IBL) where each training sample is memorized as a reference pattern. Brute-force incremental learning in IBL continuously accumulates reference patterns, which is a problem because it not only slows down the classification but also downgrades the recall performance. Regarding the latter phenomenon, we observed a tendency that as the number of reference patterns grows, some reference patterns contribute more to the false positive classification. Thus, we devised an algorithm for optimizing the reference pattern set based on the positive and negative contribution of each reference pattern. The algorithm is performed periodically to remove reference patterns that have a very low positive contribution or a high negative contribution. Experiments were performed on 6500 gesture patterns collected from 50 adults of 30~50 years old. Each alphabet was performed 5 times per participant using $Nintendo{(R)}$ $Wii^{TM}$ remote. Acceleration signal was sampled in 100hz on 3 axes. Mean recall rate for all the alphabets was 95.48%. Some alphabets recorded very low recall rate and exhibited very high pairwise confusion rate. Major confusion pairs are D(88%) and P(74%), I(81%) and U(75%), N(88%) and W(100%). Though W was recalled perfectly, it contributed much to the false positive classification of N. By comparison with major previous results from VTT (96% for 8 control gestures), CMU (97% for 10 control gestures) and Samsung Electronics(97% for 10 digits and a control gesture), we could find that the performance of our system is superior regarding the number of pattern classes and the complexity of patterns. Using our gesture interaction system, we conducted 2 case studies of robot-based edutainment services. The services were implemented on various robot platforms and mobile devices including $iPhone^{TM}$. The participating children exhibited improved concentration and active reaction on the service with our gesture interface. To prove the effectiveness of our gesture interface, a test was taken by the children after experiencing an English teaching service. The test result showed that those who played with the gesture interface-based robot content marked 10% better score than those with conventional teaching. We conclude that the accelerometer-based gesture interface is a promising technology for flourishing real-world robot-based services and content by complementing the limits of today's conventional interfaces e.g. touch screen, vision and voice.

• Investigative Magnetic Resonance Imaging
• /
• v.8 no.2
• /
• pp.79-85
• /
• 2004

Purpose : To evaluate the usefulness and reproducibility of $^1H$ MRS in different 1.5 T MR machines with different coils to compare the SNR, scan time and the spectral patterns in different brain regions in normal volunteers. Materials and Methods : Localized $^1H$ MR spectroscopy ($^1H$ MRS) was performed in a total of 10 normal volunteers (age; 20-45 years) with spectral parameters adjusted by the autoprescan routine (PROBE package). In all volunteers, MRS was performed in a three times using conventional MRS (Signa Horizon) with 1 channel coil and upgraded MRS (Echospeed plus with EXCITE) with both 1 channel and 8 channel coil. Using these three different machines and coils, SNRs of the spectra in both phantom and volunteers and (pre)scan time of MRS were compared. Two regions of the human brain (basal ganglia and deep white matter) were examined and relative metabolite ratios (NAA/Cr, Cho/Cr, and mI/Cr ratios) were measured in all volunteers. For all spectra, a STEAM localization sequence with three-pulse CHESS $H_2O$ suppression was used, with the following acquisition parameters: TR=3.0/2.0 sec, TE=30 msec, TM=13.7 msec, SW=2500 Hz, SI=2048 pts, AVG : 64/128, and NEX=2/8 (Signa/Echospeed). Results : The SNR was about over $30\%$ higher in Echospeed machine and time for prescan and scan was almost same in different machines and coils. Reliable spectra were obtained on both MRS systems and there were no significant differences in spectral patterns and relative metabolite ratios in two brain regions (p>0.05). Conclusion : Both conventional and new MRI systems are highly reliable and reproducible for $^1H$ MR spectroscopic examinations in human brains and there are no significant differences in applications for $^1H$ MRS between two different MRI systems.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.135-149
• /
• 2020

Artificial intelligences are changing world. Financial market is also not an exception. Robo-Advisor is actively being developed, making up the weakness of traditional asset allocation methods and replacing the parts that are difficult for the traditional methods. It makes automated investment decisions with artificial intelligence algorithms and is used with various asset allocation models such as mean-variance model, Black-Litterman model and risk parity model. Risk parity model is a typical risk-based asset allocation model which is focused on the volatility of assets. It avoids investment risk structurally. So it has stability in the management of large size fund and it has been widely used in financial field. XGBoost model is a parallel tree-boosting method. It is an optimized gradient boosting model designed to be highly efficient and flexible. It not only makes billions of examples in limited memory environments but is also very fast to learn compared to traditional boosting methods. It is frequently used in various fields of data analysis and has a lot of advantages. So in this study, we propose a new asset allocation model that combines risk parity model and XGBoost machine learning model. This model uses XGBoost to predict the risk of assets and applies the predictive risk to the process of covariance estimation. There are estimated errors between the estimation period and the actual investment period because the optimized asset allocation model estimates the proportion of investments based on historical data. these estimated errors adversely affect the optimized portfolio performance. This study aims to improve the stability and portfolio performance of the model by predicting the volatility of the next investment period and reducing estimated errors of optimized asset allocation model. As a result, it narrows the gap between theory and practice and proposes a more advanced asset allocation model. In this study, we used the Korean stock market price data for a total of 17 years from 2003 to 2019 for the empirical test of the suggested model. The data sets are specifically composed of energy, finance, IT, industrial, material, telecommunication, utility, consumer, health care and staple sectors. We accumulated the value of prediction using moving-window method by 1,000 in-sample and 20 out-of-sample, so we produced a total of 154 rebalancing back-testing results. We analyzed portfolio performance in terms of cumulative rate of return and got a lot of sample data because of long period results. Comparing with traditional risk parity model, this experiment recorded improvements in both cumulative yield and reduction of estimated errors. The total cumulative return is 45.748%, about 5% higher than that of risk parity model and also the estimated errors are reduced in 9 out of 10 industry sectors. The reduction of estimated errors increases stability of the model and makes it easy to apply in practical investment. The results of the experiment showed improvement of portfolio performance by reducing the estimated errors of the optimized asset allocation model. Many financial models and asset allocation models are limited in practical investment because of the most fundamental question of whether the past characteristics of assets will continue into the future in the changing financial market. However, this study not only takes advantage of traditional asset allocation models, but also supplements the limitations of traditional methods and increases stability by predicting the risks of assets with the latest algorithm. There are various studies on parametric estimation methods to reduce the estimated errors in the portfolio optimization. We also suggested a new method to reduce estimated errors in optimized asset allocation model using machine learning. So this study is meaningful in that it proposes an advanced artificial intelligence asset allocation model for the fast-developing financial markets.