• Title/Summary/Keyword: Low input management

Search Result 212, Processing Time 0.034 seconds

Measuring the Economic Impact of Item Descriptions on Sales Performance (온라인 상품 판매 성과에 영향을 미치는 상품 소개글 효과 측정 기법)

  • Lee, Dongwon;Park, Sung-Hyuk;Moon, Songchun
    • Journal of Intelligence and Information Systems
    • /
    • v.18 no.4
    • /
    • pp.1-17
    • /
    • 2012
  • Personalized smart devices such as smartphones and smart pads are widely used. Unlike traditional feature phones, theses smart devices allow users to choose a variety of functions, which support not only daily experiences but also business operations. Actually, there exist a huge number of applications accessible by smart device users in online and mobile application markets. Users can choose apps that fit their own tastes and needs, which is impossible for conventional phone users. With the increase in app demand, the tastes and needs of app users are becoming more diverse. To meet these requirements, numerous apps with diverse functions are being released on the market, which leads to fierce competition. Unlike offline markets, online markets have a limitation in that purchasing decisions should be made without experiencing the items. Therefore, online customers rely more on item-related information that can be seen on the item page in which online markets commonly provide details about each item. Customers can feel confident about the quality of an item through the online information and decide whether to purchase it. The same is true of online app markets. To win the sales competition against other apps that perform similar functions, app developers need to focus on writing app descriptions to attract the attention of customers. If we can measure the effect of app descriptions on sales without regard to the app's price and quality, app descriptions that facilitate the sale of apps can be identified. This study intends to provide such a quantitative result for app developers who want to promote the sales of their apps. For this purpose, we collected app details including the descriptions written in Korean from one of the largest app markets in Korea, and then extracted keywords from the descriptions. Next, the impact of the keywords on sales performance was measured through our econometric model. Through this analysis, we were able to analyze the impact of each keyword itself, apart from that of the design or quality. The keywords, comprised of the attribute and evaluation of each app, are extracted by a morpheme analyzer. Our model with the keywords as its input variables was established to analyze their impact on sales performance. A regression analysis was conducted for each category in which apps are included. This analysis was required because we found the keywords, which are emphasized in app descriptions, different category-by-category. The analysis conducted not only for free apps but also for paid apps showed which keywords have more impact on sales performance for each type of app. In the analysis of paid apps in the education category, keywords such as 'search+easy' and 'words+abundant' showed higher effectiveness. In the same category, free apps whose keywords emphasize the quality of apps showed higher sales performance. One interesting fact is that keywords describing not only the app but also the need for the app have asignificant impact. Language learning apps, regardless of whether they are sold free or paid, showed higher sales performance by including the keywords 'foreign language study+important'. This result shows that motivation for the purchase affected sales. While item reviews are widely researched in online markets, item descriptions are not very actively studied. In the case of the mobile app markets, newly introduced apps may not have many item reviews because of the low quantity sold. In such cases, item descriptions can be regarded more important when customers make a decision about purchasing items. This study is the first trial to quantitatively analyze the relationship between an item description and its impact on sales performance. The results show that our research framework successfully provides a list of the most effective sales key terms with the estimates of their effectiveness. Although this study is performed for a specified type of item (i.e., mobile apps), our model can be applied to almost all of the items traded in online markets.

Application of Photosynthetic Pigment Analysis Using a HPLC and CHEMTAX Program to Studies of Phytoplankton Community Composition (HPLC를 이용한 광합성색소 분석과 CHEMTAX 프로그램을 이용한 식물플랑크톤 군집조성 연구)

  • Lee, Yong-Woo;Park, Mi-Ok;Kim, Yoon-Suk;Kim, Seong-Su;Kang, Chang-Keun
    • The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
    • /
    • v.16 no.3
    • /
    • pp.117-124
    • /
    • 2011
  • Many studies of the phytoplankton community structure have been conducted using the CHEMTAX program on the basis of the photosynthetic pigment concentrations measured by a HPLC (High-Performance Liquid Chromatography) technique. The CHEMTAX program determines the contribution of each phytoplankton class to total phytoplankton biomass (chlorophyll a) based on the ratios of marker pigment to chlorophyll a of phytoplankton group. In this study, the marker pigment/chlorophyll a ratios were investigated in phytoplankton species isolated from marine waters around the Korean peninsula. These results were used as the input pigment ratios of the CHEMTAX program to investigate phytoplankton community structure in Korean coastal waters (Yeoja and Gamak Bay). There were significant differences in the ratios of marker pigment to chlorophyll a among the different species within the same algal class. There was a significant difference between the values of our ratios and the previously used ratios in other regions of the world. When phytoplankton community composition was calculated using our initial ratios in Yeoja and Gamak Bay, our results were significantly different from the results calculated on the basis of initial ratios of marker pigment in phytoplankton suggested in other marine waters. The estimates of the contributions of the major algal groups (bacillariophyceae and dinophytes) to total chlorophyll a varied within 5% depending on the initial ratios chosen. The variations of estimates for the pico- and nanoplankton (cyanophytes and prasinophytes), which have relatively low contributions to total chlorophyll a, were higher than those for major algal group. Although the HPLC-pigment measurements combined with CHEMTAX analysis are useful for identifying and qualifying phytoplankton community structure, further researches for the pigment ratios of the dominant phytoplankton species presenting in a given area are also needed.

Relationship between Fertilizer Application Level and Soil Chemical Properties for Strawberry Cultivation under Greenhouse in Chungnam Province (충남지역 시설 딸기재배지 시비수준과 토양 화학성과의 관계)

  • Choi, Moon-Tae;Lee, Jin-Il;Yun, Yeo-Uk;Lee, Jong-Eun;Lee, Bong-Chun;Yang, Euy-Seog;Lee, Young-Han
    • Korean Journal of Soil Science and Fertilizer
    • /
    • v.43 no.2
    • /
    • pp.153-159
    • /
    • 2010
  • Nowadays, Korean farmers rely more on chemical fertilizers than low input sustainable agriculture drawn from the farm itself. In order to improve soil nutritional imbalance for environment friendly agriculture in greenhouse, we have carried out a relationship between fertilizer application level, and soil chemical properties for strawberry cultivation at 56 sites in Chungnam Province. Average amount of nitrogen as basal fertilization was 92.3 Mg $ha^{-1}$ which higher 2.6 times compared to standard amount of basal fertilizer. In case of compost application more than 30 Mg $ha^{-1}$, excessive ratio compared to optimum level was higher 1.8 times for EC value, 3.0 times for available phosphate, 2.6 times for exchangeable potassium, 1.7 times for exchangeable calcium, and 1.6 times for exchangeable magnesium, respectively. Amounts of compost application significantly correlated with available phosphate (r=0.370, $p{\leq}0.01$), exchangeable potassium(r=0.429, $p{\leq}0.01$), exchangeable calcium(r=0.404, $p{\leq}0.01$), exchangeable magnesium(r=0.453, $p{\leq}0.01$), and exchangeable sodium(r=0.369, $p{\leq}0.01$), respectively. Our results suggest that soil nutrients management for sustainable agriculture was optimum fertilization based on soil testing for strawberry cultivation in greenhouse.

A Basic Study for Sustainable Analysis and Evaluation of Energy Environment in Buildings : Focusing on Energy Environment Historical Data of Residential Buildings (빌딩의 지속가능 에너지환경 분석 및 평가를 위한 기초 연구 : 주거용 건물의 에너지환경 실적정보를 중심으로)

  • Lee, Goon-Jae
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.18 no.1
    • /
    • pp.262-268
    • /
    • 2017
  • The energy consumption of buildings is approximately 20.5% of the total energy consumption, and the interest in energy efficiency and low consumption of the building is increasing. Several studies have performed energy analysis and evaluation. Energy analysis and evaluation are effective when applied in the initial design phase. In the initial design phase, however, the energy performance is evaluated using general level information, such as glazing area and surface area. Therefore, the evaluation results of the detailed design stage, which is based on the drawings, including detailed information of the materials and facilities, will be different. Thus far, most studies have reported the analysis and evaluation at the detailed design stage, where detailed information about the materials installed in the building becomes clear. Therefore, it is possible to improve the accuracy of the energy environment analysis if the energy environment information generated during the life cycle of the building can be established and accurate information can be provided in the analysis at the initial design stage using a probability / statistical method. On the other hand, historical data on energy use has not been established in Korea. Therefore, this study performed energy environment analysis to construct the energy environment historical data. As a result of the research, information classification system, information model, and service model for acquiring and providing energy environment information that can be used for building lifecycle information of buildings are presented and used as the basic data. The results can be utilized in the historical data management system so that the reliability of analysis can be improved by supplementing the input information at the initial design stage. If the historical data is stacked, it can be used as learning data in methods, such as probability / statistics or artificial intelligence for energy environment analysis in the initial design stage.

Soil Salinity and Vegetation Distribution at Four Tidal Reclamation Project Areas (4개 간척 지구에 분포하는 식생과 토양 염류농도)

  • Lee, Seung-Heon;Ji, Kwang-Jae;An, Yeoul;Ro, Hee-Myong
    • Korean Journal of Environmental Agriculture
    • /
    • v.22 no.2
    • /
    • pp.79-86
    • /
    • 2003
  • This research was conducted to present reference data to be used as newly reclaimed tidal land management. We investigated vegetation succession at 4 reclaimed/reclaiming project areas and discussed relationship with soil and vegetation trhrough investigation and analysis soil chemical characteristics at 2 areas. 14 families 58 kinds were investigated. Vegetation were variou at Dea-Ho conservation polt and Seok-Mun National Industrial Area which are maintaining naturally. Vegetation were simple at Hong-Bo and Dongjin and MinKyong river areas which effected sea water. Common species that were investigated at 9 sites were Suaeda asparagoides, Aster tripolium, Phragmites australis, Suaeda maritima, Suaeda japonica, Carex scabrifolis. As soil desalinization progressing, soil classified at first saline-soidc soil, the nest saline soil and then normal soil. Chenopodiaceae revealed at about 30 dS/m of soil ECe and existed to 10 dS/m of soil ECe. At about 20 dS/m of soil ECe. Aster tripolium, Calamagrostis epigeios, and Sonchus brachyotus revealed and then non-halophytes and common plants at inland revealed at low soil ECe of about 10 dS/m. However it was not to progress vegetation sucdession and soil desalinization at the same time, owing to input of seeds or plants ect from out-ecosystem. So for promotion of vegetation at newly reclaimed tidal land, we proposed that it was very effective to plant artificially halophytes or suitable species through soil test.

Recent Progress in Air-Conditioning and Refrigeration Research : A Review of Papers Published in the Korean Journal of Air-Conditioning and Refrigeration Engineering in 2013 (설비공학 분야의 최근 연구 동향 : 2013년 학회지 논문에 대한 종합적 고찰)

  • Lee, Dae-Young;Kim, Sa Ryang;Kim, Hyun-Jung;Kim, Dong-Seon;Park, Jun-Seok;Ihm, Pyeong Chan
    • Korean Journal of Air-Conditioning and Refrigeration Engineering
    • /
    • v.26 no.12
    • /
    • pp.605-619
    • /
    • 2014
  • This article reviews the papers published in the Korean Journal of Air-Conditioning and Refrigeration Engineering during 2013. It is intended to understand the status of current research in the areas of heating, cooling, ventilation, sanitation, and indoor environments of buildings and plant facilities. Conclusions are as follows. (1) The research works on the thermal and fluid engineering have been reviewed as groups of fluid machinery, pipes and relative parts including orifices, dampers and ducts, fuel cells and power plants, cooling and air-conditioning, heat and mass transfer, two phase flow, and the flow around buildings and structures. Research issues dealing with home appliances, flows around buildings, nuclear power plant, and manufacturing processes are newly added in thermal and fluid engineering research area. (2) Research works on heat transfer area have been reviewed in the categories of heat transfer characteristics, pool boiling and condensing heat transfer and industrial heat exchangers. Researches on heat transfer characteristics included the results for general analytical model for desiccant wheels, the effects of water absorption on the thermal conductivity of insulation materials, thermal properties of Octadecane/xGnP shape-stabilized phase change materials and $CO_2$ and $CO_2$-Hydrate mixture, effect of ground source heat pump system, the heat flux meter location for the performance test of a refrigerator vacuum insulation panel, a parallel flow evaporator for a heat pump dryer, the condensation risk assessment of vacuum multi-layer glass and triple glass, optimization of a forced convection type PCM refrigeration module, surface temperature sensor using fluorescent nanoporous thin film. In the area of pool boiling and condensing heat transfer, researches on ammonia inside horizontal smooth small tube, R1234yf on various enhanced surfaces, HFC32/HFC152a on a plain surface, spray cooling up to critical heat flux on a low-fin enhanced surface were actively carried out. In the area of industrial heat exchangers, researches on a fin tube type adsorber, the mass-transfer kinetics of a fin-tube-type adsorption bed, fin-and-tube heat exchangers having sine wave fins and oval tubes, louvered fin heat exchanger were performed. (3) In the field of refrigeration, studies are categorized into three groups namely refrigeration cycle, refrigerant and modeling and control. In the category of refrigeration cycle, studies were focused on the enhancement or optimization of experimental or commercial systems including a R410a VRF(Various Refrigerant Flow) heat pump, a R134a 2-stage screw heat pump and a R134a double-heat source automotive air-conditioner system. In the category of refrigerant, studies were carried out for the application of alternative refrigerants or refrigeration technologies including $CO_2$ water heaters, a R1234yf automotive air-conditioner, a R436b water cooler and a thermoelectric refrigerator. In the category of modeling and control, theoretical and experimental studies were carried out to predict the performance of various thermal and control systems including the long-term energy analysis of a geo-thermal heat pump system coupled to cast-in-place energy piles, the dynamic simulation of a water heater-coupled hybrid heat pump and the numerical simulation of an integral optimum regulating controller for a system heat pump. (4) In building mechanical system research fields, twenty one studies were conducted to achieve effective design of the mechanical systems, and also to maximize the energy efficiency of buildings. The topics of the studies included heating and cooling, HVAC system, ventilation, and renewable energies in the buildings. Proposed designs, performance tests using numerical methods and experiments provide useful information and key data which can improve the energy efficiency of the buildings. (5) The field of architectural environment is mostly focused on indoor environment and building energy. The main researches of indoor environment are related to infiltration, ventilation, leak flow and airtightness performance in residential building. The subjects of building energy are worked on energy saving, operation method and optimum operation of building energy systems. The remained studies are related to the special facility such as cleanroom, internet data center and biosafety laboratory. water supply and drain system, defining standard input variables of BIM (Building Information Modeling) for facility management system, estimating capability and providing operation guidelines of subway station as shelter for refuge and evaluation of pollutant emissions from furniture-like products.

Development of High-frequency Data-based Inflow Water Temperature Prediction Model and Prediction of Changesin Stratification Strength of Daecheong Reservoir Due to Climate Change (고빈도 자료기반 유입 수온 예측모델 개발 및 기후변화에 따른 대청호 성층강도 변화 예측)

  • Han, Jongsu;Kim, Sungjin;Kim, Dongmin;Lee, Sawoo;Hwang, Sangchul;Kim, Jiwon;Chung, Sewoong
    • Journal of Environmental Impact Assessment
    • /
    • v.30 no.5
    • /
    • pp.271-296
    • /
    • 2021
  • Since the thermal stratification in a reservoir inhibits the vertical mixing of the upper and lower layers and causes the formation of a hypoxia layer and the enhancement of nutrients release from the sediment, changes in the stratification structure of the reservoir according to future climate change are very important in terms of water quality and aquatic ecology management. This study was aimed to develop a data-driven inflow water temperature prediction model for Daecheong Reservoir (DR), and to predict future inflow water temperature and the stratification structure of DR considering future climate scenarios of Representative Concentration Pathways (RCP). The random forest (RF)regression model (NSE 0.97, RMSE 1.86℃, MAPE 9.45%) developed to predict the inflow temperature of DR adequately reproduced the statistics and variability of the observed water temperature. Future meteorological data for each RCP scenario predicted by the regional climate model (HadGEM3-RA) was input into RF model to predict the inflow water temperature, and a three-dimensional hydrodynamic model (AEM3D) was used to predict the change in the future (2018~2037, 2038~2057, 2058~2077, 2078~2097) stratification structure of DR due to climate change. As a result, the rates of increase in air temperature and inflow water temperature was 0.14~0.48℃/10year and 0.21~0.41℃/10year,respectively. As a result of seasonal analysis, in all scenarios except spring and winter in the RCP 2.6, the increase in inflow water temperature was statistically significant, and the increase rate was higher as the carbon reduction effort was weaker. The increase rate of the surface water temperature of the reservoir was in the range of 0.04~0.38℃/10year, and the stratification period was gradually increased in all scenarios. In particular, when the RCP 8.5 scenario is applied, the number of stratification days is expected to increase by about 24 days. These results were consistent with the results of previous studies that climate change strengthens the stratification intensity of lakes and reservoirs and prolonged the stratification period, and suggested that prolonged water temperature stratification could cause changes in the aquatic ecosystem, such as spatial expansion of the low-oxygen layer, an increase in sediment nutrient release, and changed in the dominant species of algae in the water body.

A Study on the Application of Physical Soil Washing Technology at Lead-contaminated Shooting Range in a Closed Military Shooting Range Area (폐 공용화기사격장 내 납오염 사격장 군부지의 물리적 토양세척정화기술 적용성 연구)

  • Jung, Jaeyun;Jang, Yunyoung
    • Journal of Environmental Impact Assessment
    • /
    • v.28 no.5
    • /
    • pp.492-506
    • /
    • 2019
  • Heavy metal contaminants in the shooting range are mostly present in a warhead circle or a metal fragment present as a particle, these fine metal particles are weathered for a long period of time is very likely that the surface is present as an oxide or carbon oxide. In particular, lead which is a representative contaminant in the shooting range soil, is present as more fine particles because it increases the softness and is stretched well. Therefore, by physical washing experiment, we conducted a degree analysis, concentration of heavy metals by cubic diameter, composition analysis of metallic substances, and assessment of applicability of gravity, magnetism and floating selection. The experimental results FESEM analysis and the measurement results lead to the micro-balance was confirmed thatthe weight goes outless than the soil ofthe same size in a thinly sliced and side-shaped structure according to the dull characteristics it was confirmed that the high specific gravity applicability. In addition, the remediation efficiency evaluation results using a hydrocyclone applied to this showed a cumulative remediation efficiency of 71%,twice 80%, 3 times 91%. On the other hand, magnetic sifting showed a low efficiency of 17%,floating selection -35mesh (0.5mm)target soil showed a relatively high efficiency to 39% -10mesh (2mm) efficiency was only 16%. The target treatment diameter of soil washing should be 2mm to 0.075mm, which is applied to the actual equipment by adding an additional input classification, which would require management as additional installation costs and processes are constructed. As a result, it is found that the soilremediation of shooting range can be separately according to the size of the warhead. The size is larger than the gravel diameter to most 5.56mm, so it is possible to select a specific gravity using a high gravity. However, the contaminants present in the metal fragments were found to be processed by separating using a hydrocyclone of the soil washing according to the weight is less than the soil of the same particle size in a thinly fragmented structure.

Application of Support Vector Regression for Improving the Performance of the Emotion Prediction Model (감정예측모형의 성과개선을 위한 Support Vector Regression 응용)

  • Kim, Seongjin;Ryoo, Eunchung;Jung, Min Kyu;Kim, Jae Kyeong;Ahn, Hyunchul
    • Journal of Intelligence and Information Systems
    • /
    • v.18 no.3
    • /
    • pp.185-202
    • /
    • 2012
  • .Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

A Hybrid SVM Classifier for Imbalanced Data Sets (불균형 데이터 집합의 분류를 위한 하이브리드 SVM 모델)

  • Lee, Jae Sik;Kwon, Jong Gu
    • Journal of Intelligence and Information Systems
    • /
    • v.19 no.2
    • /
    • pp.125-140
    • /
    • 2013
  • We call a data set in which the number of records belonging to a certain class far outnumbers the number of records belonging to the other class, 'imbalanced data set'. Most of the classification techniques perform poorly on imbalanced data sets. When we evaluate the performance of a certain classification technique, we need to measure not only 'accuracy' but also 'sensitivity' and 'specificity'. In a customer churn prediction problem, 'retention' records account for the majority class, and 'churn' records account for the minority class. Sensitivity measures the proportion of actual retentions which are correctly identified as such. Specificity measures the proportion of churns which are correctly identified as such. The poor performance of the classification techniques on imbalanced data sets is due to the low value of specificity. Many previous researches on imbalanced data sets employed 'oversampling' technique where members of the minority class are sampled more than those of the majority class in order to make a relatively balanced data set. When a classification model is constructed using this oversampled balanced data set, specificity can be improved but sensitivity will be decreased. In this research, we developed a hybrid model of support vector machine (SVM), artificial neural network (ANN) and decision tree, that improves specificity while maintaining sensitivity. We named this hybrid model 'hybrid SVM model.' The process of construction and prediction of our hybrid SVM model is as follows. By oversampling from the original imbalanced data set, a balanced data set is prepared. SVM_I model and ANN_I model are constructed using the imbalanced data set, and SVM_B model is constructed using the balanced data set. SVM_I model is superior in sensitivity and SVM_B model is superior in specificity. For a record on which both SVM_I model and SVM_B model make the same prediction, that prediction becomes the final solution. If they make different prediction, the final solution is determined by the discrimination rules obtained by ANN and decision tree. For a record on which SVM_I model and SVM_B model make different predictions, a decision tree model is constructed using ANN_I output value as input and actual retention or churn as target. We obtained the following two discrimination rules: 'IF ANN_I output value <0.285, THEN Final Solution = Retention' and 'IF ANN_I output value ${\geq}0.285$, THEN Final Solution = Churn.' The threshold 0.285 is the value optimized for the data used in this research. The result we present in this research is the structure or framework of our hybrid SVM model, not a specific threshold value such as 0.285. Therefore, the threshold value in the above discrimination rules can be changed to any value depending on the data. In order to evaluate the performance of our hybrid SVM model, we used the 'churn data set' in UCI Machine Learning Repository, that consists of 85% retention customers and 15% churn customers. Accuracy of the hybrid SVM model is 91.08% that is better than that of SVM_I model or SVM_B model. The points worth noticing here are its sensitivity, 95.02%, and specificity, 69.24%. The sensitivity of SVM_I model is 94.65%, and the specificity of SVM_B model is 67.00%. Therefore the hybrid SVM model developed in this research improves the specificity of SVM_B model while maintaining the sensitivity of SVM_I model.