• Journal of Gastric Cancer
• /
• v.6 no.3
• /
• pp.154-160
• /
• 2006

Purpose: According to the 2nd English Edition of the Japanese Gastric Cancer Association (JGCA) in 1998, in case of distal gastric cancer, the 14v (superior mesenteric vein) lymph node (LN) is included in the N2 group. However, in Korea, a modified radical gastrectomy is performed, and a 14v LN dissection is not done as a routine procedure. Thus, we investigated the rate of metastatic 14v LNs, evaluated the necessity of dissection of the 14v LN, and searched for indications of 14v LN dissection. Materials and Methods: From April 2004 to August 2005, we enrolled the patients who were diagnosed as having advanced gastric cancer in the distal third portion of the stomach. We peformed a distal gastrectomy with D2 lymph node dissection as defined in the 2nd English edition of the JGCA classification. We calculated the positive rate of metastatic LNs of each station and analyzed the relationship between the positive rates of No.6 LNs and 14v LNs. We also compared the positive 14v LN group with the negative 14v LN group. Results: The total number of patients was 50, the mean age was 56 (range $30{\sim}80$) years, and sex ratio (Male/Female) was 1.63 : 1. In 47 (94%) cases, distal a gastrectomy with gastroduodenostomy was done, and in the remaining 3 (6%) cases, a distal gastrectomy with gastrojejunostomy was done. The most frequently metastatic LNs were nos. 3 and 6 (54%). The metastatic rate of the f4v LN was 10%, which was similar to that of LN no. 9. In the comparison of the 14v positive group with the 14v negative group, there were significant differences in the numbers of metastatic LNs (mean 25.4 vs 4.91, P<0.001) and the numbers of metastatic no. 6 LNs, (mean 6.8 vs 1.42, P<0.001), and if no. 6 LNs were metastatic, the possibility of metastasis to the 14v LN was 19.2%. In the 14v positive group, all cases were more than stage 3 by the UICC 6th edition. Conclusion: In cases of advanced cancer with metastasis to the no. 6 IN, there was a good chance of metastasis to the 14v LN. Thus, in the operative field, if the tumor is advanced to more than stage 3 by the UICC classification and the no. 6 LN is metastatic, a 14v LN dissection is necessary. However, the usefulness of a 14v LN dissection should be evaluated prospectively through an analysis of tumor recurrence and long-term survival.

• Journal of Gastric Cancer
• /
• v.6 no.3
• /
• pp.146-153
• /
• 2006

Purpose: Gastrointestinal stromal tumorsm (GISTs) are the most common mesenchymal tumors that arise anywhere in the tubular GI tract. The prognosis for GSTIs is important because f GISTs may metastasiwx in the liver or the abdominal cavity in an early stage. For the reason we examined the tumor size, the mitotic number, ki 67, p53, and c-kit mutation as independent prognostic factor for GISTs. Materials and Methods: A retrospective study was conducted in 76 patients who had been re-evaluated for confirmation of diagnosis between Jan 1998 and Dec. 2001. at Catholic University of medicine. Results: There were significant difference between the turner size, mitotic indices, ki 67, c-kit mutations and the 5-years survival rates. Tumor size (${\geq}5\;cm$) and mitotic index (${\geq}5/50\;HPF$) were statistically related to a significantly poor prognosis (P=0.017 and P=0.042, respectively). c-kit mutations in exon 11 were found in 7 cases c-kit mutation was observed more frequently in high risk patients, and there was a significant difference between c-kit mutation and survival (P=0.037). Elevated ki 67 was noted in 34 out of the 76 cases. High risk patients showed elevated ki67 index more frequently and there was significant relation with the survival rate (P=0.0417). Conclusion: We think that tumor size, mitotic index, Ki 67 and c-kit mutation are as independent prognostic factors for GISTs, but more research is needed.

• Journal of Gastric Cancer
• /
• v.8 no.1
• /
• pp.20-26
• /
• 2008

Purpose: Pylorus-preserving gastrectomy (PPG), which retains pyloric ring and gastric function, has been accepted as a function-preserving procedure for early gastric cancer for the prevention of postgastrectomy syndrome. This study was compared laparoscopy-assisted pylorus-preerving gastrectomy (LAPPG) with laparoscopy-assisted distal gastrectomy with Billroth-I reconstruction (LADGB I). Materials and Methods: Between November 2006 and September 2007, 39 patients with early gastric cancer underwent laparoscopy-assisted gastrectomy in the Department of Surgery at Korea Cancer Center Hospital. 9 of these patients underwent LAPPG and 18 underwent LADGBI. When LAPPG was underwent, we preserved the pyloric branch, hepatic branch, and celiac branch of the vagus nerve, the infrapyloric artery, and the right gastric artery and performed D1+$\beta$ lymphadenectomy to the exclusion of suprapyloric lymph node dissection. The distal stomach was resected while retaining a $2.5{\sim}3.0\;cm$ pyloric cuff and maintaining a $3.0{\sim}4.0\;cm$ distal margin for the resection. Results: The mean age for patients who underwent LAPPG and LADGBI were $59.9{\pm}9.4$ year-old and $64.1{\pm}10.0$ year-old, respectively. The sex ratio was 1.3 : 1.0 (male 5, female 4) in the LAPPG group and 2.6 : 1.0 (male 13, female 5) in the LADGBI group. Mean total number of dissected lymph nodes ($28.3{\pm}11.9$ versus $28.1{\pm}8.9$), operation time ($269.0{\pm}34.4$ versus $236.3{\pm}39.6$ minutes), estimated blood loss ($191.1{\pm}85.7$ versus $218.3{\pm}150.6\;ml$), time to first flatus ($3.6{\pm}0.9$ versus $3.5{\pm}0.8$ days), time to start of diet ($5.1{\pm}0.9$ versus $5.1{\pm}1.7$ days), and postoperative hospital stay ($10.1{\pm}4.0$ versus $9.2{\pm}3.0$ days) were not found significant differences (P>0.05). The postoperative complications were 1 patient with gastric stasis and 1 patient with wound seroma in LAPPG group and 1 patient with left lateral segment infarct of liver in the LADGB I group. Conclusion: Patients treated by LAPPG showed a comparable quality of surgical operation compared with those treated by LADGBI. LAPPG has an important role in the surgical management of early gastric cancer in terms of quality of postoperative life. Randomized controlled studies should be undertaken to analyze the optimal survival and long-term outcomes of this operative procedure.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.3 no.1
• /
• pp.26-27
• /
• 1978

It can be expected that intelligence and knowledge will be the core of the post-industrial society in a near future. Accordingly, the age of intelligence shall be accelerated extensively to find ourselves in an age of 'Communication' service enterprise. The communication actions will increase its efficiency and multiply its utility, indebted to its scientic principles and legal idea. The two basic elements of communication action, that is, communication station and communication men are considered to perform their function when they are properly supported and managed by the government administration. Since the communication action itself is composed of various factors, the elements such as communication stations and officials must be cultivated and managed by specialist or experts with continuous and extensive study practices concerned. With the above mind, this study reviewed our public service officials law with a view to improve it by providing some suggestions for communication experts and researchers to find suitable positions in the framework of government administration. In this study, I would like to suggest 'Occupational Group of Communication' that is consisted of a series of comm, management positions and research positions in parallel to the existing series of comm, technical position. The communication specialist or expert is required to be qualified with necessary scientific knowledge and techniques of communication, as well as prerequisites as government service officials. Communication experts must succeed in the first hand to obtain government licence concerned in with the government law and regulation, and international custom before they can be appointed to the official positions. This system of licence-prior-to-appointment is principally applied in the communication management position. And communication research positions are for those who shall engage themselves to the work of study and research in the field of both management and technical nature. It is hopefully expected that efficient and extensive management of communication activities, as well as scientific and continuous study over than communication enterprise will be upgraded at national dimensions.

• KDI Journal of Economic Policy
• /
• v.12 no.1
• /
• pp.31-68
• /
• 1990

The concentration of economic power takes the form of one or a few firms controlling a substantial portion of the economic resources and means in a certain economic area. At the same time, to the extent that these firms are owned by a few individuals, resource allocation can be manipulated by them rather than by the impersonal market mechanism. This will impair allocative efficiency, run counter to a decentralized market system and hamper the equitable distribution of wealth. Viewed from the historical evolution of Western capitalism in general, the concentration of economic power is a paradox in that it is a product of the free market system itself. The economic principle of natural discrimination works so that a few big firms preempt scarce resources and market opportunities. Prominent historical examples include trusts in America, Konzern in Germany and Zaibatsu in Japan in the early twentieth century. In other words, the concentration of economic power is the outcome as well as the antithesis of free competition. As long as judgment of the economic system at large depends upon the value systems of individuals, therefore, the issue of how to evaluate the concentration of economic power will inevitably be tinged with ideology. We have witnessed several different approaches to this problem such as communism, fascism and revised capitalism, and the last one seems to be the only surviving alternative. The concentration of economic power in Korea can be summarily represented by the "jaebol," namely, the conglomerate business group, the majority of whose member firms are monopolistic or oligopolistic in their respective markets and are owned by particular individuals. The jaebol has many dimensions in its size, but to sketch its magnitude, the share of the jaebol in the manufacturing sector reached 37.3% in shipment and 17.6% in employment as of 1989. The concentration of economic power can be ascribed to a number of causes. In the early stages of economic development, when the market system is immature, entrepreneurship must fill the gap inherent in the market in addition to performing its customary managerial function. Entrepreneurship of this sort is a scarce resource and becomes even more valuable as the target rate of economic growth gets higher. Entrepreneurship can neither be readily obtained in the market nor exhausted despite repeated use. Because of these peculiarities, economic power is bound to be concentrated in the hands of a few entrepreneurs and their business groups. It goes without saying, however, that the issue of whether the full exercise of money-making entrepreneurship is compatible with social mores is a different matter entirely. The rapidity of the concentration of economic power can also be traced to the diversification of business groups. The transplantation of advanced technology oriented toward mass production tends to saturate the small domestic market quite early and allows a firm to expand into new markets by making use of excess capacity and of monopoly profits. One of the reasons why the jaebol issue has become so acute in Korea lies in the nature of the government-business relationship. The Korean government has set economic development as its foremost national goal and, since then, has intervened profoundly in the private sector. Since most strategic industries promoted by the government required a huge capacity in technology, capital and manpower, big firms were favored over smaller firms, and the benefits of industrial policy naturally accrued to large business groups. The concentration of economic power which occured along the way was, therefore, not necessarily a product of the market system. At the same time, the concentration of ownership in business groups has been left largely intact as they have customarily met capital requirements by means of debt. The real advantage enjoyed by large business groups lies in synergy due to multiplant and multiproduct production. Even these effects, however, cannot always be considered socially optimal, as they offer disadvantages to other independent firms-for example, by foreclosing their markets. Moreover their fictitious or artificial advantages only aggravate the popular perception that most business groups have accumulated their wealth at the expense of the general public and under the behest of the government. Since Korea stands now at the threshold of establishing a full-fledged market economy along with political democracy, the phenomenon called the concentration of economic power must be correctly understood and the roles of business groups must be accordingly redefined. In doing so, we would do better to take a closer look at Japan which has experienced a demise of family-controlled Zaibatsu and a success with business groups(Kigyoshudan) whose ownership is dispersed among many firms and ultimately among the general public. The Japanese case cannot be an ideal model, but at least it gives us a good point of departure in that the issue of ownership is at the heart of the matter. In setting the basic direction of public policy aimed at controlling the concentration of economic power, one must harmonize efficiency and equity. Firm size in itself is not a problem, if it is dictated by efficiency considerations and if the firm behaves competitively in the market. As long as entrepreneurship is required for continuous economic growth and there is a discrepancy in entrepreneurial capacity among individuals, a concentration of economic power is bound to take place to some degree. Hence, the most effective way of reducing the inefficiency of business groups may be to impose competitive pressure on their activities. Concurrently, unless the concentration of ownership in business groups is scaled down, the seed of social discontent will still remain. Nevertheless, the dispersion of ownership requires a number of preconditions and, consequently, we must make consistent, long-term efforts on many fronts. We can suggest a long list of policy measures specifically designed to control the concentration of economic power. Whatever the policy may be, however, its intended effects will not be fully realized unless business groups abide by the moral code expected of socially responsible entrepreneurs. This is especially true, since the root of the problem of the excessive concentration of economic power lies outside the issue of efficiency, in problems concerning distribution, equity, and social justice.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.41 no.9
• /
• pp.1265-1273
• /
• 2012

The purpose of this study was to investigate the BMI, intake of snacks, and perceptions and use of food and nutrition labels by middle school students (144 boys and 189 girls) in Chuncheon area. The average height and weight of boys were $171.0{\pm}6.4$ cm and $61.0{\pm}11.4$ kg, respectively, whereas those of girls were $160.0{\pm}4.8$ cm and $50.8{\pm}6.6$ kg, respectively. Average body mass index (BMI) of boys and girls were $20.8{\pm}3.3$ and $19.8{\pm}2.4$, respectively (p<0.01). Dietary intake attitude score of girls ($34.39{\pm}5.66$) was higher than that of boys ($33.92{\pm}5.40$) (p<0.05). Subjects bought and ate snacks 1 to 3 times per week (40.2%) by themselves, and most consumed snacks were cookies (23.1%), instant noodles (16.2%), ice cream (13.2%), and candy and chocolates (13.2%). The most important factor in purchasing of snacks was 'taste' ($4.49{\pm}0.67$). When subjects bought processed foods, the rates of reading food labels was 86.6%. The most important factor of the food labels was 'expiration date' (42.9%). The degree of reading food labels on processed foods by girls ($22.70{\pm}5.72$) was higher than that of boys ($20.96{\pm}5.35$) (p<0.01). Of the 13.2% of subjects that did not read food labels, the reason why was that they were not interested (50.0%). Of the 78.4% of subjects that read nutrition labels, the most important component of the nutrition labels was 'calories' (75.9%). The main reason for reading nutrition labels was 'to control weight' (45.6%). In general, use of food labels correlated positively with dietary intake attitude score (p<0.05) and use of nutrition labels (p<0.01). Using multiple regression analysis, we found that 'usefulness of dietary life' was the most significant variable that affects the importance of food and nutrition labels. Therefore, development of an educational program on food and nutrition labels for adolescents will be effective in improving dietary life.

• The korean journal of orthodontics
• /
• v.25 no.4
• /
• pp.465-485
• /
• 1995

The purpose of this study is to locate the proper position of the lower occlusal plane according to individual skeletal pattern. Cephalometric films of 234 subjects of the control group, 358 of the pretreatment group and 358 of the treated group were analyzed to study proper relationships between vertical dimension ratio(VDR) and lower occlusomandibular plane angle(LOM). The control group was divided into two subgroups by the age. The first subgroup consisted of 113 subjects of the age 14 years and under and with the mean age of 10.82 years. The other subgroup consisted of 113 subjects of the age 18 years and above with the mean age of 23.76 years. The pretreatment group was divided into three subgroups by the age. The first subgroup consisted of 274 subjects of the age 14 years and under with the mean age of 11.36 years. The second subgroup consisted of 54 subjects of the age 14 through 18 years with the mean age of 15.4 years. The last subgroup consisted of 30 subjects of the age 18 years and above with the mean age of 21.35 years. The treated group was also divided into three subgroups by the age. The first subgroup consisted of 145 subjects of the age 14 years and under with the mean age of 12.91 years. The second subgroup consisted of 166 subjects of the age 14 through 18 years with the mean age of 15.64 years. The last subgroup consisted of 47 subjects of the age 18 years and above with the mean age of 21.61 years. Cephalometric films of the sample were traced. Measurements were made to a hundredth using a program specifically prepared for this study, and the results were entered into a 486DX PC. Means and Standard deviations of all the veriables were calculated for each group. Correlation coefficients between pertinent variables were calculated. Significance tests on those coefficients, one-way ANOVA and t-tests between variables or groups were performed. On the basis of the results studied above, certain subjects were selected from the control and the treated groups to locate the proper position of the occlusal plane, and designated as the optimal occluaion group. The subjects of this optimal occlusion group had 1-3 mm overbite, 1-3 mm of overjet and less than 1.75 mm of curve of Spee. A total subjects of 187 in this group consisted 104 treated subjects and 83 control group. Regression analysis was carried out between VDR and LOM, and regression equations were tabulated for this optimal occlusion group. The results were as follows : 1. Highly significant correlations were observed between various variables useful for identifying vertical component of skeletal frame, but any one particular variable did not accurately indicate the magnitude of anterior vertical overbite. 2. Of the variables useful identifying vertical component of skeletal frame, The VDR showed the highest correlation to the LOM. 3. Of the total sample, 80 percent had overbite within the normal range, irrespective of VDR. 4. The optimal occlusion group was divided into 9 subgroups by the age and the anteroposterior skeletal pattern, and correlation coefficient and determination coefficient between VDR and LOM of each group were calculated. Correlation coefficients and determination coefficients were found to be significantly high in all groups. 5. Regression equation was induced for each of the optimal occlusion group to find proper LOM according to the VDR. 6. It was found that the mean value of the cant of occlusal plane itself is not enough for a diagnosis and a treatment plan. Rather, It is very important to locate the proper occlusal plane for an Individual skeletal pattern.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.85-109
• /
• 2018

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.221-241
• /
• 2018

Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.