• Journal of the Korean Society of Food Science and Nutrition
• /
• v.35 no.5
• /
• pp.549-556
• /
• 2006

The purpose of this study was to assess the effects of mulberry leaf extract supplement on blood glucose, glycated hemoglobin ($HbA_{1C}$) and serum lipids in type II diabetic patients, and also to assess safety in liver function after mulberry leaf extract supplement. The study was a randomized placebo-controlled trial and total 23 type II diabetic patients were divided into a MLE group taking 1,000 mg mulberry leaf extract supplement per day as experimental group and a placebo group taking 1,000 mg cellulose Powder supplement per day for 12 weeks. After 2 weeks of wash-out period, fasting blood glucose, $HbA_{1C}$, serum lipid levels and liver function test were analyzed before and after treatment of 12 weeks. The general baseline characteristics, nutrient intake and life style factors of study subjects were similar between two groups during intervention. The concentrations of fasting blood glucose and $HbA_{1C}$ (p<0.05) decreased significantly after mulberry leaf extract supplement in MLE group, while there were no changes found in placebo group. We also found it showed that mulberry leaf extract supplement for 12 weeks decreased significantly (p<0.05) the fasting blood glucose in poor fasting blood glucose group and $HbA_{1C}$ concentration in poor $HbA_{1C}$ group. The concentrations of LDL-cholesterol (p<0.05) and triglyceride (p<0.01) decreased significantly in MLE group after 12 weeks of taking the supplement, while there were no changes found in placebo group. The mulberry leaf extract supplement for 12 weeks didn't show hepatotoxicity. These results suggested that mulberry leaf extract supplement could be effective in improving fasting blood glucose and $HbA_{1C}$ levels in the diabetic patients, specially having high concentrations of fasting blood glucose and $HbA_{1C}$ among type II diabetic patients.

• Childhood Kidney Diseases
• /
• v.5 no.2
• /
• pp.136-146
• /
• 2001

Purpose : One of the most difficult problems in the care of children with nephrotic syndrome remains the occurrence of relapses, despite initial response to steroids. Constantinescu reported that rapidity of initial response to steroid therapy could predict fewer relapses in the first year. So we evaluated the changes in serum lipid abnormalities in children with corticosensitive nephrotic syndrome before steroid treatment and the correlation between serum lipid levels and renal function, days to remission. Methods . We analyzed the Medical records of children who were managed by us between October 1994 and August 2000. In 33 patients with corticosensitive nephrotic syndrome, we evaluated the correlation between serum lipid levels and renal function [Creatinine clearance(Ccr)] and proteinuria before steroid treatment, and days to remission defined as the third day when the patient's urine becomes protein free. Results : There were 21 males and 12 females. Median age at presentation was 6.4 years (range: 1.8-17.3 years). Median days to remission were 15.4 days (range 4-42 days) on Prednisolone $60mg/m^2$ daily. The increased levels of triglyceride, total cholesterol, LDL cholesterol, apolipoprotein B, total cholesterol/HDL cholesterol, Lipoprotein(a) were observed. But the level of HDL cholesterol was not increased. Serum albumin was decreased a]id proteinuria was increased before steroid treatment. But Ccr was not decreased. There were negative correlation between serum albumin and total cholesterol (r = -0.5157, P<0.005), LDL cholesterol (r = -0.5543, P<0.005), total cholesterol/HDL cholesterol (r = -0.4506, P<0.01), lipoprotein(a) (r = -0.4570, P<0.025), apolipoprotein B (r = -0.5297, P<0.025), apolipoprotein B/apolipoprotein Al (r = -0.5851, P<0.01), apolipoprotein B/HDL cholesterol (r = -0.4961, P<0.05) before steroid treatment. There was no correlation between proteinuria and serum lipid profiles. Also Ccr and serum lipid profiles were not correlated. There was positive correlation between days to remission and HDL cholesterol (r = +0.4511, P<0.05), apolipoprotein B (r = +0.5190, P<0.05), apolipoprotein B/HDL cholesterol (r = +0.7169, P<0.005). Conclusions : This results reveal that HDL cholesterol, apolipoprotein B and apolipoprotein B/HDL cholesterol can be used as a predictive factor in corticosensitive nephrotic syndrome. We could not determine the significant level of these lipids for insufficient patients number, but these level may predict future relapses of corticosensitive nephrotic syndrome patients and thus may allow to better management and treatment protocols. More data and long term follow up studies should be needed. (J Korean Soc Pediatr Nephrol 2001;5 : 136-46)

• Journal of Distribution Research
• /
• v.16 no.4
• /
• pp.1-27
• /
• 2011

Introduction: Sales of private labels(PU have been growing m recent years. Globally, PLs have already achieved 20% share, although between 25 and 50% share in most of the European markets(AC. Nielson, 2005). These products are aimed to have comparable quality and prices as national brand(NB) products and have been continuously eroding manufacturer's national brand market share. Stores have also started introducing premium PLs that are of higher-quality and more reasonably priced compared to NBs. Worldwide, many retailers already have a multiple-tier private label architecture. Consumers as a consequence are now able to have a more diverse brand choice in store than ever before. Since premium PLs are priced higher than regular PLs and even, in some cases, above NBs, stores can expect to generate higher profits. Brand extensions and private label have been extensively studied in the marketing field. However, less attention has been paid to the private label extension. Therefore, this research focuses on private label extension using the Multi-Attribute Attitude Model(Fishbein and Ajzen, 1975). Especially there are few studies that consider the hierarchical effect of the PL's two parent brands: store brand and the original PL. We assume that the attitude toward each of the two parent brands affects the attitude towards the extended PL. The influence from each parent brand toward extended PL will vary according to the perceived fit between each parent brand and the extended PL. This research focuses on how these two parent brands act as reference points to one another in the consumers' choice consideration. Specifically we seek to understand how store image and attitude towards original PL affect consumer perceptions of extended premium PL. How consumers perceive extended premium PLs could provide strategic suggestions for retailer managers with specific suggestions on whether it is more effective: to position extended premium PL similarly or dissimilarly to original PL especially on the quality dimension and congruency with store image. There is an extensive body of research on branding and brand extensions (e.g. Aaker and Keller, 1990) and more recently on PLs(e.g. Kumar and Steenkamp, 2007). However there are no studies to date that look at the upgrading and influence of original PLs and attitude towards store on the premium PL extension. This research wishes to make a contribution to this gap using the perceived fit difference between parent brands and extended premium PL as the context. In order to meet the above objectives, we investigate which factors heighten consumers' positive attitude toward premium PL extension. Research Model and Hypotheses: When considering the attitude towards the premium PL extension, we expect four factors to have an influence: attitude towards store; attitude towards original PL; perceived congruity between the store image and the premium PL; perceived similarity between the original PL and the premium PL. We expect that all these factors have an influence on consumer attitude towards premium PL extension. Figure 1 gives the research model and hypotheses. Method: Data were collected by an intercept survey conducted on consumers at discount stores. 403 survey responses were attained (total 59.8% female, across all age ranges). Respondents were asked to respond to a series of Questions measured on 7 point likert-type scales. The survey consisted of Questions that measured: the trust towards store and the original PL; the satisfaction towards store and the original PL; the attitudes towards store, the original PL, and the extended premium PL; the perceived similarity of the original PL and the extended premium PL; the perceived congruity between the store image and the extended premium PL. Product images with specific explanations of the features of premium PL, regular PL and NB we reused as the stimuli for the Question response. We developed scales to measure the research constructs. Cronbach's alphaw as measured each construct with the reliability for all constructs exceeding the .70 standard(Nunnally, 1978). Results: To test the hypotheses, path analysis was conducted using LISREL 8.30. The path analysis for verification of the model produced satisfactory results. The validity index shows acceptable results(${\chi}^2=427.00$(P=0.00), GFI= .90, AGFI= .87, NFI= .91, RMSEA= .062, RMR= .047). With the increasing retailer use of premium PLBs, the intention of this research was to examine how consumers use original PL and store image as reference points as to the attitude towards premium PL extension. Results(see table 1 & 2) show that the attitude of each parent brand (attitudes toward store and original pL) influences the attitude towards extended PL and their perceived fit moderates these influences. Attitude toward the extended PL was influenced by the relative level of perceived fit. Discussion of results and future direction: These results suggest that the future strategy for the PL extension needs to consider that positive parent brand attitude is more strongly associated with the attitude toward PL extensions. Specifically, to improve attitude towards PL extension, building and maintaining positive attitude towards original PL is necessary. Positioning premium PL congruently to store image is also important for positive attitude. In order to improve this research, the following alternatives should also be considered. To improve the research model's predictive power, more diverse products should be included in study. Other attributes of product should also be included such as design, brand name since we only considered trust and satisfaction as factors to build consumer attitudes.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.40 no.5
• /
• pp.100-108
• /
• 2012

The purpose of the study was to evaluate the influence of shading and ventilation on Mean Radiant Temperature(MRT) of the outdoor space at a summer outdoor. The Wind Speed(WS), Air Temperature(AT) and Globe Temperature(GT) were recorded every minute from $1^{st}$ of May to the $30^{th}$ of September 2011 at a height of 1.2m above in four experimental plots with different shading and ventilating conditions, with a measuring system consisting of a vane type anemometer(Barini Design's BDTH), Resistance Temperature Detector(RTD, Pt-100), standard black globe(${\O}$ 150mm) and data acquisition systems(National Instrument's Labview and Compfile Techs' Moacon). To implement four different ventilating and shading conditions, three hexahedral steel frames, and one natural plot were established in the open grass field. Two of the steel frames had a dimension of $3m(W){\times}3m(L){\times}1.5m(H)$ and every vertical side covered with transparent polyethylene film to prevent lateral ventilation(Ventilation Blocking Plot: VP), and an additional shading curtain was applied on the top side of a frame(Shading and Ventilation Blocking Plot: SVP). The third was $1.5m(W){\times}1.5m(L){\times}1.5m(H)$, only the top side of which was covered by the shading curtain without the lateral film(Shading Plot: SP). The last plot was natural condition without any kind of shading and wind blocking material(Natural Open Plot: NP). Based on the 13,262 records of 44 sunny days, the time serial difference of AT and GT for 24 hour were analyzed and compared, and statistical analysis was done based on the 7,172 records of daytime period from 7 A.M. to 8 P.M., while the relation between the MRT and solar radiation and wind speed was analyzed based on the records of the hottest period from 11 A.M. to 4 P.M.. The major findings were as follows: 1. The peak AT was $40.8^{\circ}C$ at VP and $35.6^{\circ}C$ at SP showing the difference about $5^{\circ}C$, but the difference of average AT was very small within${\pm}1^{\circ}C$. 2. The difference of the peak GT was $12^{\circ}C$ showing $52.5^{\circ}C$ at VP and $40.6^{\circ}C$ at SP, while the gap of average GT between the two plots was $6^{\circ}C$. Comparing all four plots including NP and SVP, it can be said that the shading decrease $6^{\circ}C$ GT while the wind blocking increase $3^{\circ}C$ GT. 3. According to the calculated MRT, the shading has a cooling effect in reducing a maximum of $13^{\circ}C$ and average $9^{\circ}C$ MRT, while the wind blocking has heating effect of increasing average $3^{\circ}C$ MRT. In other words, the MRT of the shaded area with natural ventilation could be cooler than the wind blocking the sunny site to about $16^{\circ}C$ MRT maximum. 4. The regression and correlation tests showed that the shading is more important than the ventilation in reducing the MRT, while both of them do an important role in improving the outdoor thermal comfort. In summary, the results of this study showed that the shade is the first and the ventilation is the second important factor in terms of improving outdoor thermal comfort in summer daylight hours. Therefore, it can be apparently said that the more shade by the forest, shading trees etc., the more effective in conditioning the microclimate of an outdoor space reducing the useless or even harmful heat energy for human activities. Furthermore, the delicately designed wind corridor or outdoor ventilation system can improve even the thermal environment of urban area.

• Journal of Chest Surgery
• /
• v.42 no.4
• /
• pp.480-486
• /
• 2009

Background: The Fogarty thromboembolectomy catheter technique was devised to extract distal arterial emboli and it represents a milestone for the treatment of patients with acute arterial occlusion since the 1960s. The major causes of arterial occlusion have changed from emboli of a heart origin to atherosclerosis over the past 30 years. Accordingly, questions have been raised about the effectiveness of simple Fogarty thromboembolectomy. Material and Method: During the period from March 1990 through August 2008, 156 patients who requiring Fogarty thromboembolectomy were analyzed. The patients were divided into two groups: those with simple Fogarty thromboembolectomy (Group 1, 79 patients) and those with additional vascular bypass graft surgery (Group 2, 77 patients). The duration of symptoms, the cause of thrombi, admission via the emergency room, a history of acupuncture or misdiagnosis, combined diseases, the anatomic occlusion site and the cause of death were analyzed using T-tests, cross tab tests, Chi square tests and Kaplan-Meier tests, respectively. Result: The mean age was 64$\pm$10 years in the 2 groups. The duration of symptoms (pain) in Group 1 vs Group 2 was 12$\pm$4 days vs 71$\pm$14 days (p=0.001). 50 (63%) patients in Group 1 were admitted via the emergency room vs 18 (23%) patients in Group 2 (p=0.005). Misdiagnosis and the treatment for herniated intervertebral disc or acupuncture were given to, 20 (25%) patients in Group 1 vs 30 (39%) patients in Group 2. Anticoagulation treatment before admission was performed in 22 (28%) patients in Group 1 vs 11 (14%) patients in Group 2. The causes of thrombi were heart disease in, 24 (30%) patients in Group 1 vs 6 (8%) patients in Group 2 (p=0.001), atherosclerosis in 46 (58%) patients in Group 1 vs 67 (87%) patients in Group 2 (p=0.001) and trauma in 9 (11%) patients in Group 1 vs 6 (8%) patients in Group 2. The combined diseases were cerebrovascular accident, hypertension and diabetes mellitus in 22 $\sim$ 37% of the total patients. The occlusion sites were mainly in the iliac and femoral arteries. Endarterectomy was performed in 7 (9%) patients in Group 1 vs 18 (23%) patients in Group 2 (p=0.012). Treatment was successful in 27 (34%) patients in Group 1 and in 40 (52%) patients in Group 2 (p=0.019). Reocclusion occurred in 37(47%) patients in Group 1 vs 20 (26%) patients in Group 2 (p=0.000), Amputation was done in 4 (5%) patients in Group 1 vs 12 (16%) patients in Group 2 (p=0.012) and death occurred in 10 (13%) patients (Group 1) vs 3(4%) patients (Group 2) (p=0.044). Conclusion: The recent past has shown a decline in the effectiveness of simple Fogarty thromboembolectomy with a changing pattern of acute arterial occlusion from a rheumatic heart origin to atherosclerosis. Additional bypass procedures play a role for the treatment of arterial occlusion instead of always performing simple Fogarty thromboembolectomy.

• Korean Journal of Soil Science and Fertilizer
• /
• v.45 no.5
• /
• pp.853-860
• /
• 2012

To estimate potential use of fly ash in reducing $CH_4$ and $CO_2$ emission from soil, $CH_4$ and $CO_2$ fluxes from a paddy soil mixed with fly ash at different rate (w/w; 0, 5, and 10%) in the presence and absence of fertilizer N ($(NH_4)_2SO_4$) addition were investigated in a laboratory incubation for 60 days under changing water regime from wetting to drying via transition. The mean $CH_4$ flux during the entire incubation period ranged from 0.59 to $1.68mg\;CH_4\;m^{-2}day^{-1}$ with a lower rate in the soil treated with N fertilizer due to suppression of $CH_4$ production by $SO_4^{2-}$ that acts as an electron acceptor, leading to decreases in electron availability for methanogen. Fly ash application reduced $CH_4$ flux by 37.5 and 33.0% in soils without and with N addition, respectively, probably due to retardation of $CH_4$ diffusion through soil pores by addition of fine-textured fly ash. In addition, as fly ash has a potential for $CO_2$ removal via carbonation (formation of carbonate precipitates) that decreases $CO_2$ availability that is a substrate for $CO_2$ reduction reaction (one of $CH_4$ generation pathways) is likely to be another mechanisms of $CH_4$ flux reduction by fly ash. Meanwhile, the mean $CO_2$ flux during the entire incubation period was between 0.64 and $0.90g\;CO_2\;m^{-2}day^{-1}$, and that of N treated soil was lower than that without N addition. Because N addition is likely to increase soil respiration, it is not straightforward to explain the results. However, it may be possible that our experiment did not account for the substantial amount of $CO_2$ produced by heterotrophs that were activated by N addition in earlier period than the measurement was initiated. Fly ash application also lowered $CO_2$ flux by up to 20% in the soil mixed with fly ash at 10% through $CO_2$ removal by the carbonation. At the whole picture, fly ash application at 10% decreased global warming potential of emitted $CH_4$ and $CO_2$ by about 20%. Therefore, our results suggest that fly ash application can be a soil management practice to reduce green house gas emission from paddy soils. Further studies under field conditions with rice cultivation are necessary to verify our findings.

• 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.

• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.147-168
• /
• 2017

There have been many studies on accurate stock market forecasting in academia for a long time, and now there are also various forecasting models using various techniques. Recently, many attempts have been made to predict the stock index using various machine learning methods including Deep Learning. Although the fundamental analysis and the technical analysis method are used for the analysis of the traditional stock investment transaction, the technical analysis method is more useful for the application of the short-term transaction prediction or statistical and mathematical techniques. Most of the studies that have been conducted using these technical indicators have studied the model of predicting stock prices by binary classification - rising or falling - of stock market fluctuations in the future market (usually next trading day). However, it is also true that this binary classification has many unfavorable aspects in predicting trends, identifying trading signals, or signaling portfolio rebalancing. In this study, we try to predict the stock index by expanding the stock index trend (upward trend, boxed, downward trend) to the multiple classification system in the existing binary index method. In order to solve this multi-classification problem, a technique such as Multinomial Logistic Regression Analysis (MLOGIT), Multiple Discriminant Analysis (MDA) or Artificial Neural Networks (ANN) we propose an optimization model using Genetic Algorithm as a wrapper for improving the performance of this model using Multi-classification Support Vector Machines (MSVM), which has proved to be superior in prediction performance. In particular, the proposed model named GA-MSVM is designed to maximize model performance by optimizing not only the kernel function parameters of MSVM, but also the optimal selection of input variables (feature selection) as well as instance selection. In order to verify the performance of the proposed model, we applied the proposed method to the real data. The results show that the proposed method is more effective than the conventional multivariate SVM, which has been known to show the best prediction performance up to now, as well as existing artificial intelligence / data mining techniques such as MDA, MLOGIT, CBR, and it is confirmed that the prediction performance is better than this. Especially, it has been confirmed that the 'instance selection' plays a very important role in predicting the stock index trend, and it is confirmed that the improvement effect of the model is more important than other factors. To verify the usefulness of GA-MSVM, we applied it to Korea's real KOSPI200 stock index trend forecast. Our research is primarily aimed at predicting trend segments to capture signal acquisition or short-term trend transition points. The experimental data set includes technical indicators such as the price and volatility index (2004 ~ 2017) and macroeconomic data (interest rate, exchange rate, S&P 500, etc.) of KOSPI200 stock index in Korea. Using a variety of statistical methods including one-way ANOVA and stepwise MDA, 15 indicators were selected as candidate independent variables. The dependent variable, trend classification, was classified into three states: 1 (upward trend), 0 (boxed), and -1 (downward trend). 70% of the total data for each class was used for training and the remaining 30% was used for verifying. To verify the performance of the proposed model, several comparative model experiments such as MDA, MLOGIT, CBR, ANN and MSVM were conducted. MSVM has adopted the One-Against-One (OAO) approach, which is known as the most accurate approach among the various MSVM approaches. Although there are some limitations, the final experimental results demonstrate that the proposed model, GA-MSVM, performs at a significantly higher level than all comparative models.