• Asia pacific journal of information systems
• /
• v.20 no.3
• /
• pp.191-204
• /
• 2010

Recently, the CO2 emission and energy consumption have become critical global issues to decide the future of nations. Especially, the spread of IT products and the increased use of internet and web applications result in the energy consumption and CO2 emission of IT industry though information technologies drive global economic growth. EU, the United States, Japan and other developed countries are using IT related environmental regulations such as WEEE(Waste Electrical and Electronic Equipment), RoHS(Restriction of the use of Certain Hazardous Substance), REACH(Registration, Evaluation, Authorization and Restriction of CHemicals) and EuP(Energy using Product), and have established systematic green business/IT strategies to enhance the competitiveness of IT industry. For example, the Japan government proposed the "Green IT initiative" for being compatible with economic growth and environmental protection. Not only energy saving technologies but energy saving systems have been developed for accomplishing sustainable development. Korea's CO2 emission and energy consumption continuously have grown at comparatively high rates. They are related to its industrial structure depending on high energy-consuming industries such as iron and steel Industry, automotive industry, shipbuilding industry, semiconductor industry, and so on. In particular, export proportion of IT manufacturing is quite high in Korea. For example, the global market share of the semiconductor such as DRAM was about 80% in 2008. Accordingly, Korea needs to establish a systematic strategy to respond to the global environmental regulations and to maintain competitiveness in the IT industry. However, green competitiveness of Korea ranked 11th among 15 major countries and R&D budget for green technology is not large enough to develop energy-saving technologies for infrastructure and value chain of low-carbon society though that grows at high rates. Moreover, there are no concrete action plans in Korea. This research aims to deduce the priorities of the Korean green business/IT strategies to use multi attribute weighted average method. We selected a panel of 19 experts who work at the green business related firms such as HP, IBM, Fujitsu and so on, and selected six assessment indices such as the urgency of the technology development, the technology gap between Korea and the developed countries, the effect of import substitution, the spillover effect of technology, the market growth, and the export potential of the package or stand-alone products by existing literature review. We submitted questionnaires at approximately weekly intervals to them for priorities of the green business/IT strategies. The strategies broadly classify as follows. The first strategy which consists of the green business/IT policy and standardization, process and performance management and IT industry and legislative alignment relates to government's role in the green economy. The second strategy relates to IT to support environment sustainability such as the travel and ways of working management, printer output and recycling, intelligent building, printer rationalization and collaboration and connectivity. The last strategy relates to green IT systems, services and usage such as the data center consolidation and energy management, hardware recycle decommission, server and storage virtualization, device power management, and service supplier management. All the questionnaires were assessed via a five-point Likert scale ranging from "very little" to "very large." Our findings show that the IT to support environment sustainability is prior to the other strategies. In detail, the green business /IT policy and standardization is the most important in the government's role. The strategies of intelligent building and the travel and ways of working management are prior to the others for supporting environment sustainability. Finally, the strategies for the data center consolidation and energy management and server and storage virtualization have the huge influence for green IT systems, services and usage This research results the following implications. The amount of energy consumption and CO2 emissions of IT equipment including electrical business equipment will need to be clearly indicated in order to manage the effect of green business/IT strategy. And it is necessary to develop tools that measure the performance of green business/IT by each step. Additionally, intelligent building could grow up in energy-saving, growth of low carbon and related industries together. It is necessary to expand the affect of virtualization though adjusting and controlling the relationship between the management teams.

• Journal of Mushroom
• /
• v.16 no.3
• /
• pp.155-161
• /
• 2018

In this study, we analyze the growth environment using smart farm technology in order to develop the optimal growth model for the precision cultivation of the bottle-grown oyster mushroom 'Suhan'. Experimental farmers used $88m^2$ of bed area, 2 rows and 5 columns of shelf shape, 5 hp refrigerator, 100T of sandwich panel for insulation, 2 ultrasonic humidifiers, 12 kW of heating, and 5,000 bottles for cultivation. Data on parameters such as temperature, humidity, carbon dioxide concentration, and illumination, which directly affect mushroom growth, were collected from the environmental sensor part installed at the oyster mushroom cultivator and analyzed. It was found that the initial temperature at the time of granulation was $22^{\circ}C$ after the scraping, and the mushroom was produced and maintained at about $25^{\circ}C$ until the bottle was flipped. On fruiting body formation, mushrooms were harvested while maintaining the temperature between $13^{\circ}C$ and $15^{\circ}C$. Humidity was approximately 100% throughout the growth stage. Carbon dioxide concentration gradually increased until 3 days after the beginning of cultivation, and then increased rapidly to approximately 2,600 ppm. From the 6th day, $CO_2$ concentration was gradually decreased through ventilation and maintained at 1,000 ppm during the harvest. Light was not provided at the initial stage of oyster mushroom cultivation. On the $3^{rd}$ and $4^{th}$ day, mushrooms were irradiated by 17 lux light. Subsequently, the light intensity was increased to 115-120 lux as the growth progressed. Fruiting body characteristics of 'Suhan' cultivated in a farmhouse were as follows: Pileus diameter was 30.9 mm and thickness was 4.5 mm; stipe thickness was 11.0 mm and length was 76.0 mm; stipe and pileus hardness was 0.8 g/mm and 2.8 g/mm, respectively; L values of the stipe and pileus were 79.9 and 52.3, respectively. The fruiting body yield was 160.2 g/850 ml, and the individual weight was 12.8 g/10 unit.

• Korean Journal of Soil Science and Fertilizer
• /
• v.50 no.5
• /
• pp.434-451
• /
• 2017

For this study, groundwater samples for 3 years from 2011 through 2013 were collected at 106 groundwater monitoring site in Korea. These groundwater samples were analyzed for 13 pesticides such as cabofuran, pentachlorobenzene, hexachlorobenzene, simazine, atrazine, lindane (gamma-HCH), alachlor, heptachlor, chlordane (total), endosulfan (1, 2), dieldrin, endrin, 4,4-DDT. The objectives of this study were to determine the detection frequency and their concentrations of 13 pesticides and evaluate the health risk level considering ingestion, inhalation, and skin contact using concentrations of 13 pesticides in groundwater samples. An analysis was used for the simultaneous determination for 13 pesticides using GC-MS. GC-MS was performed on HP-5ms, using helium ($1ml\;min^{-1}$) as carrier gas. The average recoveries of the pesticides were from 92.8% to 120.8%. The limits of detection (LODs) were between $0.004{\mu}g\;L^{-1}$ and $0.118{\mu}g\;L^{-1}$ and the limits of quantification (LOQs) were between $0.012{\mu}g\;L^{-1}$ and $0.354{\mu}g\;L^{-1}$. 106 groundwater wells were selected. 54 wells were from well to monitor background groundwater quality and 52 wells were from well to monitor groundwater quality in industrial or contamination source area. Eight pesticides including pentachlorobenzene, lindane (Gamma-HCH), heptachlor, chlordane (total), Endosulfan (1, 2), dieldrin, endrin, and 4,4-DDT were not detected in groundwater samples. The detection frequency for hexachlorobenzene, alachlor, carbofuran and simazine was 23.4%, 11.4%, 7.3%, and 1.0%, respectively. Atrazine was detected once in 2011. The average concentrations were $0.00423{\mu}g\;L^{-1}$ for carbofuran, $0.000243{\mu}g\;L^{-1}$ for alachlor, $0.00015{\mu}g\;L^{-1}$ for simazine, and $0.00001{\mu}g\;L^{-1}$ for hexachlorobenzene. The detection frequency of hexachlorobenzene was high, but the average concentration was low. In the contaminated groundwater, the detection frequency for hexachlorobenzene, alachlor, carbofuran, simazine and atrazine was 26.1%, 21.3%, 7.1%, 1.9% and 0.3%, respectively. In the uncontaminated groundwater, detection frequency for hexachlorobenzene, carbofuran and alachlor were 20.2%, 7.5%, and 1.9% respectively. Simazine and atrazine were not detected at uncontaminated groundwater wells. According to the purpose of groundwater use, atrazine was detected for agricultural groundwater use. Hexachlorobenzene showed high detection frequency at agricultural groundwater use area where the animal feeding area and golf course area were located. Alachlor showed more than 50% detection frequency at cropping area, pollution concern river area, and golf course area. Atrazine was detected in agricultural water use area. By land use, the maximum detection frequency of alachlor was found near an orchard. For human risk assessment, the cancer risk for the 5 pesticides was between $10^{-7}$ and $10^{-10}$, while the non-cancer risk (HQ value) was between $10^{-4}$ and $10^{-6}$. For conclusion, these monitoring study needs to continue because of the possibility of groundwater contamination based on various purpose of groundwater use.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.17 no.1
• /
• pp.27-35
• /
• 2014

The headspace solid-phase microextraction (HS-SPME) followed by gas chromatography/mass spectrometry procedure has been developed for the simultaneous determination of petroleum aromatic hydrocarbons such as benzene, toluene, ethylbenzene and xylene isomers (BTEX) and polycyclic aromatic hydrocarbons (PAHs) in seawater. The advantages of SPME compared to traditional methods of sample preparation are ease of operation, reuse of fiber, portable system, minimal contamination and loss of the sample during transport and storage. SPME fiber, extraction time, temperature, stirring speed, and GC desorption time were key extraction parameters considered in this study. Among three kinds of SPME fibers, i.e., PDMS ($100{\mu}m$), CAR/PDMS ($75{\mu}m$), and PDMS/DVB ($65{\mu}m$), a $65{\mu}m$ PDMS/DVB fiber showed the most optimal extraction efficiencies covering molecular weight ranging from 78 to 202. Other extraction parameters were set up using $65{\mu}m$ PDMS/DVB. The final optimized extraction conditions were extraction time (60 min), extraction temperature (50), stirring speed (750 rpm) and GC desorption time (3 min). When applied to artificially contaminated seawater like water accommodated fraction, our optimized HS-SPME-GC/MS showed comparable performances with other conventional method. The proposed protocol can be an attractive alternative to analysis of BTEX and PAHs in seawater.

• Nuclear Engineering and Technology
• /
• v.25 no.2
• /
• pp.237-247
• /
• 1993

Activity ratio of two radioactive primary fission products which had sufficiently different half-lives was expressed as functions of cooling time and irradiation histories in which average burnup, irradiation time, cycle interval time and the dominant fissile material of the spent fuel were included. The gamma-ray spectra of 36 samples from 6 spent PWR fuel assemblies irradiated in Kori unit-1 reactor were obtained by a spectrometric system equipped with a high purity germanium gamma-ray detector. Activity ratio $^{l44}$Ce $^{l37}$Cs, analyzed from each spectrum, was used for the calculation of cooling time. The results show that the radioactive fission products $^{l44}$Ce and $^{l37}$Cs are considered as useful monitors for cooling time determination because the estimated cooling time by detection of activity ratio $^{l44}$Ce $^{l37}$Cs agreed well with the operator declared cooling time within relative difference of $\pm$5 % despite the low counting rate of the gamma-ray of $^{l44}$Ce (about 10$^{-3}$ count per second). For the samples with several different irradiation histories, the determined cooling time by modeled irradiation history showed good agreement with that by known irradiation history within time difference of $\pm$0.5 year. From this result, it would be expected to be possible to estimate reliably the cooling time of spent nuclear fuel without the exact information about irradiation history. The feasibility study on identification of and/or sorting out spent nuclear fuel by applying the technique for cooling time determination was also performed and the result shows that the detection of activity ratio $^{l44}$Ce $^{l37}$Cs by gamma-ray spectrometry would be usefully applicable to certify spent nuclear fuel for the purpose of safeguards and management in a facility in which the samples dismantled or cut from spent fuel assemblies are treated, such as the post irradiation examination facility.mination facility.

• The Journal of Fisheries Business Administration
• /
• v.26 no.2
• /
• pp.53-74
• /
• 1995

The purpose of this paper is to compare China's and Korea's marine fisheries industries in order to present the main features of China's marine fisheries and show the comparative advantages they have in production. The results indicate that China's marine fisheries have the following features. (1) The marine proportion of the fisheries industry economic activity is less than 60%. Fishing is 71.3% of that marine activity. (2) The production trends of marine fisheries history in China can be classified as follows: 1) an early growth period, 2) a deliberation/consolidation period, 3) a second growth period, 4) a third growth period, and 5) a fourth growth period. The growth rate has rapidly increased recently. (3) Fish production is over 70% of marine fishing fisheries, the next major product is crustacea. The production of shellfish occupies over 70% of marine aquaculture, seaweed production however, is only 22% of total marine aquaculture. (4) The licensed area for marine aquaculture in China is 586.3 ha and that area is 5.4 times larger than that of Korea. The allotted area for shellfish aquaculture is 60% of marine aquaculture, production areas of crustaceans occupy 27.3%, fish has 7 1%, and seaweed production only 5.7% of allocated marine aquaculture areas. (5) The proportion of power vessels for marine fisheries of China's total power vessel fleet is around 65%, and the marine fisheries portion of non - powered vessels constitutes only 12%. The highest proportion of power vessels engaged in marine fisheries activities is between 10 tonnes to 100 tonnes. (6) The portion of marine fishery workers of all fishery industry employees is 22%, and 70% of them are full - time workers. Of marine fishery workers, 64% are in the fishing sector, 22%, aquaculture workers, and the number of employees in marine fisheries is increasing every year. The analysis of China's fishery industry in the production competitiveness indicates as follows : (1) The licensed areas in marine aquaculture, number of fishing vessels, number of marine fishing workers in China's fishery industry are much more than those of Korea's. Therefore China is much more competitive than Korea in the quantity of production side. However, licensed areas for seaweed aquaculture are more extensive in Korea than China. In China, the number of power vessels of between 10 tonnes and 100 tonnes, the licensed shellfish aquaculture areas, and the number of fishing workers within the fisheries industry are much more than those of Korea. (2) It is estimated that the licensed areas in marine aquaculture, number of medium sized power vessels, number of marine fishery workers will be increased as the quantity of production factors grow in China. (3) At present, yield per Ha. in marine cultures is very low in China. Therefore it is estimated that aquaculture techniques have only been diffused recently in China. Yield of fish per Ha especially is much lower than that of Korea. So the level of aquaculture techniques seems much lower than that of Korea. (4) China is behind Korea in production technique, however the number of HP per boat in China is lower than that of Korea. Therefore, China is much more competitive than Korea in Costs. (5) Average fish catches per marine fishery worker in China is only 1/3 that of Korea's, and average marine aquaculture production in China is only 1/2 that of Korea. Therefore we can say Korea is more competitive than China in efficiency. The average income of marine fishery workers in China is higher that that of other Chinese industries. However, the competitiveness of the fisheries industry in China will be increased as more capital is invested and advanced techniques are developed.

• Journal of Global Scholars of Marketing Science
• /
• v.20 no.1
• /
• pp.98-109
• /
• 2010

Research on the construction, measurement, and management of brand equity has been extensive since David A. Aaker(1991) and Kevin Lane Keller(1993) first advanced the concept. Recently, much attention has been devoted to the components of brand equity: brand awareness, perceived quality, brand image, and brand loyalty. This study explores the relationships among these components, focusing particularly on the moderating role of product type (utilitarian vs. hedonic) in their causal relationships. A model to study the relationship among components of brand equity, particularly the moderating role of product type, is featured in Figure 1. The hypotheses of the study are proposed as follows: that consumers' brand awareness has a positive influence on brand loyalty and brand image; that consumers' perceived quality has a positive influence on brand loyalty and brand image; that consumers' brand image influences brand loyalty positively; and that relationships among components of brand equity will be moderated by product type. That is, in the case of utilitarian products, the impact of perceived quality on brand loyalty will be relatively stronger, whereas with hedonic products the impact of brand image on brand loyalty will be relatively stronger. To determine the products for the study, a pre-test of 58 college students in the Seoul metropolitan area was conducted based on the product type scale. As a result, computers were selected as the utilitarian product and blue jeans became the hedonic product. For each product type, two brands were selected: Samsung and HP for computers, and Levis and Nix for blue jeans. In the main study, 237 college students in the metropolitan area were surveyed to measure their brand awareness, perceived quality, brand image, and brand loyalty toward the selected two brands of each product type. The subjects were divided into two groups: one group (121 subjects) for computers, the other (116 subjects) for blue jeans. The survey questionnaires for the study included four parts: five questions on brand awareness and four questions each on perceived quality, brand image, and brand loyalty. All questions were to be answered using 7-point Likert scales. The data collected by the survey were processed to assess reliability and validity, and the causal relationships were analyzed to verify the hypotheses using the AMOS 7 program, a tool for analyzing structural equation modeling. A confirmatory factor analysis assessed the appropriateness of the measurement model, and the fit indices denoted that the model was satisfactory. The relationships among the components of brand equity were also analyzed using AMOS 7. The fit indices of the structural model denoted that it was also satisfactory. The paths in the structural model as will be seen in Figure 2 show that perceived quality affects brand image positively, but that brand awareness does not affect brand image. Moreover, it shows that brand awareness, perceived quality, and brand image are positively related with brand loyalty, and that this relationship is moderated by product type. In the case of utilitarian products, perceived quality has relatively more influence on brand loyalty. Conversely, in the case of hedonic products, brand image has relatively more influence on brand loyalty. The results of this empirical study contribute toward the advancement of our understanding of the relationships among the components of brand equity and expand the theoretical underpinnings for brand equity measurement. It also helps further our understanding of the effect of product type on customer-based brand equity. In a marketing management practice perspective, these results may provide managerial implications for building and maintaining brand equity effectively.

• Journal of Biosystems Engineering
• /
• v.8 no.1
• /
• pp.47-60
• /
• 1983

상온통풍(常溫通風)을 이용(利用)한 In-bin drying에 대(對)한 많은 실험결과(實驗結果)에 의(依)하면 우리나라 10월(月)의 기상조건(氣象條件)은 저온건조(低溫乾燥) system에 적합(適合)한 건조능력(乾燥能力)을 가지고 있는 것으로 나타났다. 최근(最近) Computer를 이용(利用)한 Simulation model이 개발(開發)되어 건조현상(乾操現象)에 관(關)한 경제적(經濟的)이고 효율적(效率的)인 분석(分析)이 가능(可能)하게 되었다. 이러한 분석결과(分析結果)에 의(依)하면 초기함수율(初期含水率)이 높은 벼를 Full-bin을 이용(利用)한 상온통풍건조(常溫通風乾操)를 할 경우(境遇) 건조기간(乾燥期間)이 길어지며 bin내(內)의 상층부(上層部) 곡물(穀物)이 변질(變質)되는 문제점(問題點)이 발생(發生)하였다. 또한 벼의 수확작업체계(收穫作業體系)가 관행(慣行) 및 Binder작업체계(作業體系)에서 점차(漸次) Combine작업체계(作業體系)로 전환(轉換)되어감에 따라 포장(圃場)에서의 건조(乾燥)가 어려우며 예취(刈取), 탈곡작업과정(脫穀作業過程)에서의 기계적(機械的)인 곡물(穀物) 손실(損失)을 줄이기 위(爲)하여 함수율(含水率)이 비교적(比較的) 높은 벼를 수확(收穫)하여야 한다. 본(本) 연구(硏究)의 목적(目的)은 상온통풍건조(常溫通風乾燥)에 있어서 건조능력(乾燥能力)을 증가(增加)시키기 위(爲)하여 곡물(穀物)을 일정기간(一定期間) 나누어서 bin에 넣고 건조(乾燥)를 하는 Layer drying의 Simulation model을 개발(開發)하고 이 Model에 수원지방(水原地方)의 7년간(年間) 평균(平均) 기상자료(氣象資料)를 입력(入力)시켜 곡물(穀物)의 초기함수율(初期含水率), 투입량(投入量), 투입기간(投入期間)의 변화(變化)에 따른 Layer drying현상(現象)을 규명(糾明)하는데 있다. Simulation에 사용(使用)된 bin의 크기는 직경(直徑) 2m, 깊이 1.5m이며 송풍(送風)팬의 용량(容量)은 0.5HP이었다. Simulation분석(分析) 결과(結果)를 요약(要約)하면 다음과 같다. (1) Layer drying의 Simulation model을 개발(開發)하였으며 이 Model은 벼의 상온통풍건조(常溫通風乾燥) 실험(實驗)에서 함수량(含水量) 변화(變化)의 이론치(理論値)와 실제실험치(實際實驗値)가 잘 일치(一致)하였다. (2) 곡물투입기간(穀物投入期間) 1일(日)을 Full-bin drying으로 간주(看做)할 때 Layer drying의 건조성능(乾燥性能)은 Full-bin보다 높은 것으로 나타났다. (3) 연속송풍(連續送風)(24시간(時間))을 할 경우(境遇) 곡물투입기간(穀物投入期間)이 증가(增加)함에 따라 건조기간(乾燥期間)의 감소경향(減少傾向)은 단속송풍(斷續送風)인 경우(境遇)보다 적었지만 건조기간(乾燥期間)은 단축(短縮)되었다. 그러나 건조(乾燥)에너지의 소모(消耗)는 단속송풍(斷續送風)일 때보다 크게 나타났다. (4) 단속송풍(斷續送風)(9 : 00AM~6 : 00PM)일 경우(境遇) 곡물투입기간(穀物投入期間)을 증가(增加)시키면 건조기간(乾燥期間)이 크게 줄어 들었다. (5) 곡물(穀物)의 초기함수율(初期含水率)이 21% 이하(以下)일 경우(境遇) 연속(連續) 및 단속송풍(斷續送風)에서 건조기간(乾燥期間)의 차이(差異)가 별로 없었다. (6) 곡물(穀物)의 초기함수율(初期含水率)이 높으면 Full-bin drying에서는 상부층(上部層)에 곡물(穀物)이 변질(變質)될 우려(憂慮)가 있으나 Layer drying에서는 곡물투입량(穀物投入量)을 조절(調節)하면 이것을 방지(防止)할 수 있었다. (7) 건조(乾燥)가 완료(完了)된 후(後) 층별(層別) 최종곡물(最終穀物) 함수율(含水率)은 모든 건조조건(乾燥條件)에서 동일(同一)하였으나 bin의 하부층(下部層)은 과건조(過乾燥) 물상(物象)을 일으켰다.

• The Journal of the Petrological Society of Korea
• /
• v.23 no.4
• /
• pp.293-309
• /
• 2014

The Qinling-Dabie-Sulu-Hongseong-Odesan collision belt was formed by the collision between the North China and South China Cratons during late Permian to Triassic. During the collision, Triassic post-collision igneous rocks regionally intruded in the Qinling and the Hongseong-Odesan collision belts which represent the western and eastern ends of the collision belt, respectively. However, no and minor Triassic post-collision igneous activities occur in the Dabie and Sulu belts respectively. The peak metamorphic pressure conditions along the Qinling-Dabie-Sulu-Hongseong-Odesan belt indicate that the slab break-off occurred at the depth of ultra-high pressure (UHP) metamorphic condition in the Dabie and Sulu belts and at the depths of high pressure (HP) or high pressure granulite (HPG) metamorphic condition in the Qinling and Hongseong-Odesan belts. In the Dabie and Sulu belts the heat supply from the asthenospheric mantle through the gab formed by slab break-off could not cause an extensive melting in the lower continental crust and lithospheric mantle directly below it due to the very deep depth of slab break-off. On the other hand, in the Qinling and Hongseong-Odesan belts, shallower slab break-off caused the emplacement of regional post collision igneous rocks. The post-collision igneous rocks occur in the area to the north of the Mianlu Suture zone in the western Qinling belt and crop out continuously eastwards into the areas to the north of the Shangdan Suture zone in the eastern Qinling belt through the areas within the South Qinling block. This distribution pattern of post collision igneous rocks suggests that the Triassic collision belt in the Mianleu Suture zone may be extended into the Shangdan Suture zone after passing through the South Qinling block instead into the boundary between the South Qinling block and the South China Craton.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.123-139
• /
• 2019

The Korean NPL market was formed by the government and foreign capital shortly after the 1997 IMF crisis. However, this market is short-lived, as the bad debt has started to increase after the global financial crisis in 2009 due to the real economic recession. NPL has become a major investment in the market in recent years when the domestic capital market's investment capital began to enter the NPL market in earnest. Although the domestic NPL market has received considerable attention due to the overheating of the NPL market in recent years, research on the NPL market has been abrupt since the history of capital market investment in the domestic NPL market is short. In addition, decision-making through more scientific and systematic analysis is required due to the decline in profitability and the price fluctuation due to the fluctuation of the real estate business. In this study, we propose a prediction model that can determine the achievement of the benchmark yield by using the NPL market related data in accordance with the market demand. In order to build the model, we used Korean NPL data from December 2013 to December 2017 for about 4 years. The total number of things data was 2291. As independent variables, only the variables related to the dependent variable were selected for the 11 variables that indicate the characteristics of the real estate. In order to select the variables, one to one t-test and logistic regression stepwise and decision tree were performed. Seven independent variables (purchase year, SPC (Special Purpose Company), municipality, appraisal value, purchase cost, OPB (Outstanding Principle Balance), HP (Holding Period)). The dependent variable is a bivariate variable that indicates whether the benchmark rate is reached. This is because the accuracy of the model predicting the binomial variables is higher than the model predicting the continuous variables, and the accuracy of these models is directly related to the effectiveness of the model. In addition, in the case of a special purpose company, whether or not to purchase the property is the main concern. Therefore, whether or not to achieve a certain level of return is enough to make a decision. For the dependent variable, we constructed and compared the predictive model by calculating the dependent variable by adjusting the numerical value to ascertain whether 12%, which is the standard rate of return used in the industry, is a meaningful reference value. As a result, it was found that the hit ratio average of the predictive model constructed using the dependent variable calculated by the 12% standard rate of return was the best at 64.60%. In order to propose an optimal prediction model based on the determined dependent variables and 7 independent variables, we construct a prediction model by applying the five methodologies of discriminant analysis, logistic regression analysis, decision tree, artificial neural network, and genetic algorithm linear model we tried to compare them. To do this, 10 sets of training data and testing data were extracted using 10 fold validation method. After building the model using this data, the hit ratio of each set was averaged and the performance was compared. As a result, the hit ratio average of prediction models constructed by using discriminant analysis, logistic regression model, decision tree, artificial neural network, and genetic algorithm linear model were 64.40%, 65.12%, 63.54%, 67.40%, and 60.51%, respectively. It was confirmed that the model using the artificial neural network is the best. Through this study, it is proved that it is effective to utilize 7 independent variables and artificial neural network prediction model in the future NPL market. The proposed model predicts that the 12% return of new things will be achieved beforehand, which will help the special purpose companies make investment decisions. Furthermore, we anticipate that the NPL market will be liquidated as the transaction proceeds at an appropriate price.