• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.1-32
• /
• 2018

In addition to stakeholders including managers, employees, creditors, and investors of bankrupt companies, corporate defaults have a ripple effect on the local and national economy. Before the Asian financial crisis, the Korean government only analyzed SMEs and tried to improve the forecasting power of a default prediction model, rather than developing various corporate default models. As a result, even large corporations called 'chaebol enterprises' become bankrupt. Even after that, the analysis of past corporate defaults has been focused on specific variables, and when the government restructured immediately after the global financial crisis, they only focused on certain main variables such as 'debt ratio'. A multifaceted study of corporate default prediction models is essential to ensure diverse interests, to avoid situations like the 'Lehman Brothers Case' of the global financial crisis, to avoid total collapse in a single moment. The key variables used in corporate defaults vary over time. This is confirmed by Beaver (1967, 1968) and Altman's (1968) analysis that Deakins'(1972) study shows that the major factors affecting corporate failure have changed. In Grice's (2001) study, the importance of predictive variables was also found through Zmijewski's (1984) and Ohlson's (1980) models. However, the studies that have been carried out in the past use static models. Most of them do not consider the changes that occur in the course of time. Therefore, in order to construct consistent prediction models, it is necessary to compensate the time-dependent bias by means of a time series analysis algorithm reflecting dynamic change. Based on the global financial crisis, which has had a significant impact on Korea, this study is conducted using 10 years of annual corporate data from 2000 to 2009. Data are divided into training data, validation data, and test data respectively, and are divided into 7, 2, and 1 years respectively. In order to construct a consistent bankruptcy model in the flow of time change, we first train a time series deep learning algorithm model using the data before the financial crisis (2000~2006). The parameter tuning of the existing model and the deep learning time series algorithm is conducted with validation data including the financial crisis period (2007~2008). As a result, we construct a model that shows similar pattern to the results of the learning data and shows excellent prediction power. After that, each bankruptcy prediction model is restructured by integrating the learning data and validation data again (2000 ~ 2008), applying the optimal parameters as in the previous validation. Finally, each corporate default prediction model is evaluated and compared using test data (2009) based on the trained models over nine years. Then, the usefulness of the corporate default prediction model based on the deep learning time series algorithm is proved. In addition, by adding the Lasso regression analysis to the existing methods (multiple discriminant analysis, logit model) which select the variables, it is proved that the deep learning time series algorithm model based on the three bundles of variables is useful for robust corporate default prediction. The definition of bankruptcy used is the same as that of Lee (2015). Independent variables include financial information such as financial ratios used in previous studies. Multivariate discriminant analysis, logit model, and Lasso regression model are used to select the optimal variable group. The influence of the Multivariate discriminant analysis model proposed by Altman (1968), the Logit model proposed by Ohlson (1980), the non-time series machine learning algorithms, and the deep learning time series algorithms are compared. In the case of corporate data, there are limitations of 'nonlinear variables', 'multi-collinearity' of variables, and 'lack of data'. While the logit model is nonlinear, the Lasso regression model solves the multi-collinearity problem, and the deep learning time series algorithm using the variable data generation method complements the lack of data. Big Data Technology, a leading technology in the future, is moving from simple human analysis, to automated AI analysis, and finally towards future intertwined AI applications. Although the study of the corporate default prediction model using the time series algorithm is still in its early stages, deep learning algorithm is much faster than regression analysis at corporate default prediction modeling. Also, it is more effective on prediction power. Through the Fourth Industrial Revolution, the current government and other overseas governments are working hard to integrate the system in everyday life of their nation and society. Yet the field of deep learning time series research for the financial industry is still insufficient. This is an initial study on deep learning time series algorithm analysis of corporate defaults. Therefore it is hoped that it will be used as a comparative analysis data for non-specialists who start a study combining financial data and deep learning time series algorithm.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.219-239
• /
• 2019

As the importance of providing customized services to individuals becomes important, researches on personalized recommendation systems are constantly being carried out. Collaborative filtering is one of the most popular systems in academia and industry. However, there exists limitation in a sense that recommendations were mostly based on quantitative information such as users' ratings, which made the accuracy be lowered. To solve these problems, many studies have been actively attempted to improve the performance of the recommendation system by using other information besides the quantitative information. Good examples are the usages of the sentiment analysis on customer review text data. Nevertheless, the existing research has not directly combined the results of the sentiment analysis and quantitative rating scores in the recommendation system. Therefore, this study aims to reflect the sentiments shown in the reviews into the rating scores. In other words, we propose a new algorithm that can directly convert the user 's own review into the empirically quantitative information and reflect it directly to the recommendation system. To do this, we needed to quantify users' reviews, which were originally qualitative information. In this study, sentiment score was calculated through sentiment analysis technique of text mining. The data was targeted for movie review. Based on the data, a domain specific sentiment dictionary is constructed for the movie reviews. Regression analysis was used as a method to construct sentiment dictionary. Each positive / negative dictionary was constructed using Lasso regression, Ridge regression, and ElasticNet methods. Based on this constructed sentiment dictionary, the accuracy was verified through confusion matrix. The accuracy of the Lasso based dictionary was 70%, the accuracy of the Ridge based dictionary was 79%, and that of the ElasticNet (${\alpha}=0.3$) was 83%. Therefore, in this study, the sentiment score of the review is calculated based on the dictionary of the ElasticNet method. It was combined with a rating to create a new rating. In this paper, we show that the collaborative filtering that reflects sentiment scores of user review is superior to the traditional method that only considers the existing rating. In order to show that the proposed algorithm is based on memory-based user collaboration filtering, item-based collaborative filtering and model based matrix factorization SVD, and SVD ++. Based on the above algorithm, the mean absolute error (MAE) and the root mean square error (RMSE) are calculated to evaluate the recommendation system with a score that combines sentiment scores with a system that only considers scores. When the evaluation index was MAE, it was improved by 0.059 for UBCF, 0.0862 for IBCF, 0.1012 for SVD and 0.188 for SVD ++. When the evaluation index is RMSE, UBCF is 0.0431, IBCF is 0.0882, SVD is 0.1103, and SVD ++ is 0.1756. As a result, it can be seen that the prediction performance of the evaluation point reflecting the sentiment score proposed in this paper is superior to that of the conventional evaluation method. In other words, in this paper, it is confirmed that the collaborative filtering that reflects the sentiment score of the user review shows superior accuracy as compared with the conventional type of collaborative filtering that only considers the quantitative score. We then attempted paired t-test validation to ensure that the proposed model was a better approach and concluded that the proposed model is better. In this study, to overcome limitations of previous researches that judge user's sentiment only by quantitative rating score, the review was numerically calculated and a user's opinion was more refined and considered into the recommendation system to improve the accuracy. The findings of this study have managerial implications to recommendation system developers who need to consider both quantitative information and qualitative information it is expect. The way of constructing the combined system in this paper might be directly used by the developers.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.63-83
• /
• 2019

Investors prefer to look for trading points based on the graph shown in the chart rather than complex analysis, such as corporate intrinsic value analysis and technical auxiliary index analysis. However, the pattern analysis technique is difficult and computerized less than the needs of users. In recent years, there have been many cases of studying stock price patterns using various machine learning techniques including neural networks in the field of artificial intelligence(AI). In particular, the development of IT technology has made it easier to analyze a huge number of chart data to find patterns that can predict stock prices. Although short-term forecasting power of prices has increased in terms of performance so far, long-term forecasting power is limited and is used in short-term trading rather than long-term investment. Other studies have focused on mechanically and accurately identifying patterns that were not recognized by past technology, but it can be vulnerable in practical areas because it is a separate matter whether the patterns found are suitable for trading. When they find a meaningful pattern, they find a point that matches the pattern. They then measure their performance after n days, assuming that they have bought at that point in time. Since this approach is to calculate virtual revenues, there can be many disparities with reality. The existing research method tries to find a pattern with stock price prediction power, but this study proposes to define the patterns first and to trade when the pattern with high success probability appears. The M & W wave pattern published by Merrill(1980) is simple because we can distinguish it by five turning points. Despite the report that some patterns have price predictability, there were no performance reports used in the actual market. The simplicity of a pattern consisting of five turning points has the advantage of reducing the cost of increasing pattern recognition accuracy. In this study, 16 patterns of up conversion and 16 patterns of down conversion are reclassified into ten groups so that they can be easily implemented by the system. Only one pattern with high success rate per group is selected for trading. Patterns that had a high probability of success in the past are likely to succeed in the future. So we trade when such a pattern occurs. It is a real situation because it is measured assuming that both the buy and sell have been executed. We tested three ways to calculate the turning point. The first method, the minimum change rate zig-zag method, removes price movements below a certain percentage and calculates the vertex. In the second method, high-low line zig-zag, the high price that meets the n-day high price line is calculated at the peak price, and the low price that meets the n-day low price line is calculated at the valley price. In the third method, the swing wave method, the high price in the center higher than n high prices on the left and right is calculated as the peak price. If the central low price is lower than the n low price on the left and right, it is calculated as valley price. The swing wave method was superior to the other methods in the test results. It is interpreted that the transaction after checking the completion of the pattern is more effective than the transaction in the unfinished state of the pattern. Genetic algorithms(GA) were the most suitable solution, although it was virtually impossible to find patterns with high success rates because the number of cases was too large in this simulation. We also performed the simulation using the Walk-forward Analysis(WFA) method, which tests the test section and the application section separately. So we were able to respond appropriately to market changes. In this study, we optimize the stock portfolio because there is a risk of over-optimized if we implement the variable optimality for each individual stock. Therefore, we selected the number of constituent stocks as 20 to increase the effect of diversified investment while avoiding optimization. We tested the KOSPI market by dividing it into six categories. In the results, the portfolio of small cap stock was the most successful and the high vol stock portfolio was the second best. This shows that patterns need to have some price volatility in order for patterns to be shaped, but volatility is not the best.

• Journal of Distribution Science
• /
• v.10 no.3
• /
• pp.51-61
• /
• 2012

This study seeks to understand how the choice of a coffee shop is related to a customer's loyalty and which characteristics of a shop influence this choice. It considers large-sized coffee shops brands whose market scale has gradually grown. The users' choice of shop is determined by price, employee service, shop location, and shop atmosphere. The study investigated the effects of these four properties on the brand attitudes of coffee shops. The effects were found to vary depending on users' characteristics. The properties with the largest influence were shop atmosphere and shop location Therefore, the purpose of the study was to examine the properties that could help coffee shops get loyal customers, and the choice properties that could satisfy consumers' desires The study examined consumers' perceptions of shop properties at selection of coffee shop and the difference between perceptual difference and coffee brand in order to investigate customers' desires and needs and to suggest ways that could supply products and service. The research methodology consisted of two parts: normative and empirical research, which includes empirical analysis and statistical analysis. In this study, a statistical analysis of the empirical research was carried out. The study theoretically confirmed the shop choice properties by reviewing previous studies and performed an empirical analysis including cross tabulation based on secondary material. The findings were as follows: First, coffee shop choice properties varied by gender. Price advantage influenced the choice of both men and women; men preferred nearer coffee shops where they could buy coffee easily and more conveniently than women did. The atmosphere of the coffee shop had the greatest influence on both men and women, and shop atmosphere was thought to be the most important for age analysis. In the past, customers selected coffee shops solely to drink coffee. Now, they select the coffee shop according to its interior, menu variety, and atmosphere owing to improved quality and service of coffee shop brands. Second, the prices of the brands did not vary much because the coffee shops were similarly priced. The service was thought to be more important and to elevate service quality so that price and employee service and other properties did not have a great influence on shop choice. However, those working in the farming, forestry, fishery, and livestock industries were more concerned with the price than the shop atmosphere. College and graduate school students were also affected by inexpensive price. Third, shop choice properties varied depending on income. The shop location and shop atmosphere had a greater influence on shop choice. The customers in an income bracket of less than 2 million won selected low-price coffee shops more than those earning 6 million won or more. Therefore, price advantage had no relation with difference in income. The higher income group was not affected by employee service. Fourth, shop choice properties varied depending on place. For instance, customers at Ulsan were the most affected by the price, and the ones at Busan were the least affected. The shop location had the greatest influence among all of the properties. Among the places surveyed, Gwangju had the least influence. The alternate use of space in a coffee shop was thought to be important in all the cities under consideration. The customers at Ulsan were not affected by employee service, and they selected coffee shops according to quality and preference of shop atmosphere. Lastly, the price factor was found to be a little higher than other factors when customers frequently selected brands according to shop properties. Customers at Gwangju reacted to discounts more than those in other cities did, and the former gave less priority to the quality and taste of coffee. Brand preference varied depending on coffee shop location. Customers at Busan selected brands according to the coffee shop location, and those at Ulsan were not influenced by employee kindness and specialty. The implications of this study are that franchise coffee shop businesses should focus on customers rather than aggressive marketing strategies that increase the number of coffee shops. Thus, they should create an environment with a good atmosphere and set up coffee shops in places that customers have good access to. This study has some limitations. First, the respondents were concentrated in metropolitan areas. Secondary data showed that the number of respondents at Seoul was much more than that at Gyeonggi-do. Furthermore, the number of respondents at Gyeonggi-do was much more than those at the six major cities in the nation. Thus, the regional sample was not representative enough of the population. Second, respondents' ratio was used as a measurement scale to test the perception of shop choice properties and brand preference. The difficulties arose when examining the relation between these properties and brand preference, as well as when understanding the difference between groups. Therefore, future research should seek to address some of the shortcomings of this study: If the coffee shops are being expanded to local areas, then a questionnaire survey of consumers at small cities in local areas shall be conducted to collect primary material. In particular, variables of the questionnaire survey shall be measured using Likert scales in order to include perception on shop choice properties, brand preference, and repurchase. Therefore, correlation analysis, multi-regression, and ANOVA shall be used for empirical analysis and to investigate consumers' attitudes and behavior in detail.

• Journal of Global Scholars of Marketing Science
• /
• v.18 no.4
• /
• pp.1-32
• /
• 2008

Brown and Dacin (1997) have investigated the relationship between corporate associations and product evaluations. Their study focused on the effects of associations with a company's corporate ability (CA) and its corporate social responsibility (CSR) on consumers' product evaluations. Their study has found that both of CA and CSR influenced product evaluation but CA association has a stronger effect than CSR associations. Brown and Dacin (1997) have, however, claimed that there are few researches on how corporate association impacts product responses. Accordingly, some of researchers have found the variables to moderate or to mediate the relationship between the corporate association and the product responses. In particular, there has been existed a few of studies that tested the influence of the reputation on the product-relevant perceived risk, but the effects of two types of the corporate association on the product-relevant perceived risk were not identified so far. The primary goal of this article is to identify and empirically examine some variables to moderate the effects of CA association and CSR association on the perceived risk of the product. In this articles, we take the concept of the corporate associations that Brown and Dacin (1997) had proposed. CA association is those association related to the company's expertise in producing and delivering its outputs and CSR association reflected the organization's status and activities with respect to its perceived societal obligations. Also, this study defines the risk, which is the uncertainty or loss of the product and corporate that consumers have taken in a particular purchase decision or after having purchased. The risk is classified into product-relevant performance risk and financial risk. Performance risk is the possibility or the consequence of a product not functioning at some expected level and financial risk is the monetary loss one perceives to be incurring if a product does not function at some expected level. In relation to consumer's knowledge, expert consumers have much of the experiences or knowledge of the product in consumer position and novice consumers does not. The model tested in this article are shown in Figure 1. The model indicates that both of CA association and CSR association influence on performance risk and financial risk. In addition, the effects of CA and CSR are moderated by product category knowledge (product knowledge) and product category involvement (product involvement). In this study, the relationships between the corporate association and product-relevant perceived risk are hypothesized as the following form. For example, Hypothesis 1a($H_{1a}$) is represented that CA association has a positive influence on the performance risk of consumer. Also, the hypotheses that identified some variables to moderate the effects of two types of corporate association on the perceived risk of the product are laid down. One of the hypotheses of the interaction effect is Hypothesis 3a($H_{3a}$), it is described that consumer's knowledges of the product moderates the negative relationship between CA association and product-relevant performance risk. A field experiment was conducted in order to examine our model. The company tested was not real but imagined to meet the internal validity. Water purifiers were used for our study. Four scenarios have been developed and described as the imaginary company: Type A with both of superior CA and CSR, Type B with superior CSR and inferior CA, Type C with superior CA and inferior CSR, and Type D with both inferior of CA and CSR. The respondents of this study were classified into four groups. One type of four scenarios (Type A, B, C, or D) in its questionnaire was given to the respondent who filled out questions. Data were collected by means of a self-administered questionnaire to the respondents, chosen in convenience. A total of 300 respondents filled out the questionnaire but 207 were used for further analysis. Table 1 indicates that the scales in this study are reliable because the range of coefficients of Cronbach's $\alpha$ are from 0.85 to 0.92. The composite reliability is in the range of 0,85 to 0,92 and average variance extracted is in 0.72-0.98 range that is higher than the base level of 0.6. As shown in Table 2, the values for CFI, NNFI, root-mean-square error approximation (RMSEA), and standardized root-mean-square residual (SRMR) are acceptably close to the standards suggested by Hu and Bentler (1999):.95 for CFI and NNFI,.06 for RMSEA, and.08 for SRMR. We also tested discriminant validity provided by Fornell and Larcker (1981). As shown in Table 2, we found strong evidence for discriminant validity between each possible pair of latent constructs in all samples. Given that these batteries of overall goodness-of-fit indices were accurate and that the model was developed on theoretical bases, and given the high level of consistency across samples, this enables us to proceed the previously defined scales. We used the moderated hierarchical regression analysis to test the influence of the corporate association(CA and CSR associations) on product-relevant perceived risk(performance and financial risks) and to identify the variables moderating the relationship between the corporate association and product-relevant performance risk. In this study, dependent variables are performance and financial risk. CA and CSR associations are described the independent variables. The moderating variables are product category knowledge and product category involvement. The results are, as expected, found that CA association has statistically a significant influence on the perceived risk of the product, but CSR association does not. Product category knowledge and involvement moderate the relationship between the CA association and the perceived risk of the product. However, the effect of CSR association on the perceived risk of the product is not moderated by the consumers' knowledge and involvement. For this result, it is necessary for a corporate to inform its customers CA association more than CSR association so that they could be felt to be the reduction of the perceived risk. The important theoretical contribution of this research is the meanings that two types of corporate association that Brown and Dacin(1997), and Brown(1998) have proposed replicated the difference of the effects on product evaluation. According to Hunter(2001), it was an important affair to accomplish the validity of a particular study and we had to take about ten studies to deduce a strict study. Next, there is the contribution of the this study to find that the effects of corporate association on the perceived risk of the product are varied by the moderator variables. In particular, the moderating effect of knowledge on the relationship between corporate association and product-relevant perceived risk has not been tested in Korea. In the managerial implications of this research, we suggest the necessity to stress the ability that corporate manufactures the product well(CA association) than the accomplishment of corporate's social obligation(CSR association). This study suffers from various limitations that imply future research directions. The moderating effects of product category knowledge and involvement on the relationship between corporate association and perceived risk need to be replicated. Next, future research could explore whether the mediated effects of the perceived risk has the relationship between corporate association and consumer's product purchase. In addition, to ensure the external validity of the study will be needed to use realistic company, not artificial.

• Asia Marketing Journal
• /
• v.14 no.2
• /
• pp.65-96
• /
• 2012

Brand has received much attention from considerable marketing research. When consumers consume product or services, they are exposed to a lot of brand related stimuli. These contain brand personality, brand experience, brand identity, brand communications and so on. A special kind of new crisis occasionally confronting companies' brand management today is the brand related rumor. An important influence on consumers' purchase decision making is the word-of-mouth spread by other consumers and most decisions are influenced by other's recommendations. In light of this influence, firms have reasonable reason to study and understand consumer-to-consumer communication such as brand rumor. The importance of brand rumor to marketers is increasing as the number of internet user and SNS(social network service) site grows. Due to the development of internet technology, people can spread rumors without the limitation of time, space and place. However relatively few studies have been published in marketing journals and little is known about brand rumors in the marketplace. The study of rumor has a long history in all major social science. But very few studies have dealt with the antecedents and consequences of any kind of brand rumor. Rumor has been generally described as a story or statement in general circulation without proper confirmation or certainty as to fact. And it also can be defined as an unconfirmed proposition, passed along from people to people. Rosnow(1991) claimed that rumors were transmitted because people needed to explain ambiguous and uncertain events and talking about them reduced associated anxiety. Especially negative rumors are believed to have the potential to devastate a company's reputation and relations with customers. From the perspective of marketer, negative rumors are considered harmful and extremely difficult to control in general. It is becoming a threat to a company's sustainability and sometimes leads to negative brand image and loss of customers. Thus there is a growing concern that these negative rumors can damage brands' reputations and lead them to financial disaster too. In this study we aimed to distinguish antecedents of brand rumor transmission and investigate the effects of brand rumor characteristics on rumor spread intention. We also found key components in personal acceptance of brand rumor. In contextualist perspective, we tried to unify the traditional psychological and sociological views. In this unified research approach we defined brand rumor's characteristics based on five major variables that had been found to influence the process of rumor spread intention. The five factors of usefulness, source credibility, message credibility, worry, and vividness, encompass multi level elements of brand rumor. We also selected product involvement as a control variable. To perform the empirical research, imaginary Korean 'Kimch' brand and related contamination rumor was created and proposed. Questionnaires were collected from 178 Korean samples. Data were collected from college students who have been experienced the focal product. College students were regarded as good subjects because they have a tendency to express their opinions in detail. PLS(partial least square) method was adopted to analyze the relations between variables in the equation model. The most widely adopted causal modeling method is LISREL. However it is poorly suited to deal with relatively small data samples and can yield not proper solutions in some cases. PLS has been developed to avoid some of these limitations and provide more reliable results. To test the reliability using SPSS 16 s/w, Cronbach alpha was examined and all the values were appropriate showing alpha values between .802 and .953. Subsequently, confirmatory factor analysis was conducted successfully. And structural equation modeling has been used to analyze the research model using smartPLS(ver. 2.0) s/w. Overall, R² of adoption of rumor is .476 and R² of intention of rumor transmission is .218. The overall model showed a satisfactory fit. The empirical results can be summarized as follows. According to the results, the variables of brand rumor characteristic such as source credibility, message credibility, worry, and vividness affect argument strength of rumor. And argument strength of rumor also affects rumor intention. On the other hand, the relationship between perceived usefulness and argument strength of rumor is not significant. The moderating effect of product involvement on the relations between argument strength of rumor and rumor W.O.M intention is not supported neither. Consequently this study suggests some managerial and academic implications. We consider some implications for corporate crisis management planning, PR and brand management. This results show marketers that rumor is a critical factor for managing strong brand assets. Also for researchers, brand rumor should become an important thesis of their interests to understand the relationship between consumer and brand. Recently many brand managers and marketers have focused on the short-term view. They just focused on strengthen the positive brand image. According to this study we suggested that effective brand management requires managing negative brand rumors with a long-term view of marketing decisions.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.165-183
• /
• 2016

Over the past decade, there has been a rapid diffusion of technological devices and a rising number of various devices, resulting in an escalation of virtual reality technology. Technological market has rapidly been changed from smartphone to wearable devices based on virtual reality. Virtual reality can make users feel real situation through sensing interaction, voice, motion capture and so on. Facebook.com, Google, Samsung, LG, Sony and so on have investigated developing platform of virtual reality. the pricing of virtual reality devices also had decreased into 30% from their launched period. Thus market infrastructure in virtual reality have rapidly been developed to crease marketplace. However, most consumers recognize that virtual reality is not ease to purchase or use. That could not lead consumers to positive attitude for devices and purchase the related devices in the early market. Through previous studies related to virtual reality, there are few studies focusing on why the devices for virtual reality stayed in early stage in adoption & diffusion context in the market. Almost previous studies considered the reasons of hard adoption for innovative products in the viewpoints of Typology of Innovation Resistance, MIR(Management of Innovation Resistant), UTAUT & UTAUT2. However, product-based antecedents also important to increase user intention to purchase and use products in the technological market. In this study, we focus on user acceptance and resistance for increasing purchase and usage promotions of wearable devices related to virtual reality based on headgear products like Galaxy Gear. Especially, we added a variables like attitude confidence as a dimension for user resistance. The research questions of this study are follows. First, how attitude confidence and innovativeness resistance affect user intention to use? Second, What factors related to content and brand contexts can affect user intention to use? This research collected data from the participants who have experiences using virtual rality headgears aged between 20s to 50s located in South Korea. In order to collect data, this study used a pilot test and through making face-to-face interviews on three specialists, face validity and content validity were evaluated for the questionnaire validity. Cleansing the data, we dropped some outliers and data of irrelevant papers. Totally, 156 responses were used for testing the suggested hypotheses. Through collecting data, demographics and the relationships among variables were analyzed through conducting structural equation modeling by PLS. The data showed that the sex of respondents who have experience using social commerce sites (male=86(55.1%), female=70(44.9%). The ages of respondents are mostly from 20s (74.4%) to 30s (16.7%). 126 respondents (80.8%) have used virtual reality devices. The results of our model estimation are as follows. With the exception of Hypothesis 1 and 7, which deals with the two relationships between brand awareness to attitude confidence, and quality of content to perceived enjoyment, all of our hypotheses were supported. In compliance with our hypotheses, perceived ease of use (H2) and use innovativeness (H3) were supported with its positively influence for the attitude confidence. This finding indicates that the more ease of use and innovativeness for devices increased, the more users' attitude confidence increased. Perceived price (H4), enjoyment (H5), Quantity of contents (H6) significantly increase user resistance. However, perceived price positively affect user innovativeness resistance meanwhile perceived enjoyment and quantity of contents negatively affect user innovativeness resistance. In addition, aesthetic exterior (H6) was also positively associated with perceived price (p<0.01). Also projection quality (H8) can increase perceived enjoyment (p<0.05). Finally, attitude confidence (H10) increased user intention to use virtual reality devices. however user resistance (H11) negatively affect user intention to use virtual reality devices. The findings of this study show that attitude confidence and user innovativeness resistance differently influence customer intention for using virtual reality devices. There are two distinct characteristic of attitude confidence: perceived ease of use and user innovativeness. This study identified the antecedents of different roles of perceived price (aesthetic exterior) and perceived enjoyment (quality of contents & projection quality). The findings indicated that brand awareness and quality of contents for virtual reality is not formed within virtual reality market yet. Therefore, firms should developed brand awareness for their product in the virtual market to increase market share.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.123-138
• /
• 2017

Since the stock market is driven by the expectation of traders, studies have been conducted to predict stock price movements through analysis of various sources of text data. In order to predict stock price movements, research has been conducted not only on the relationship between text data and fluctuations in stock prices, but also on the trading stocks based on news articles and social media responses. Studies that predict the movements of stock prices have also applied classification algorithms with constructing term-document matrix in the same way as other text mining approaches. Because the document contains a lot of words, it is better to select words that contribute more for building a term-document matrix. Based on the frequency of words, words that show too little frequency or importance are removed. It also selects words according to their contribution by measuring the degree to which a word contributes to correctly classifying a document. The basic idea of constructing a term-document matrix was to collect all the documents to be analyzed and to select and use the words that have an influence on the classification. In this study, we analyze the documents for each individual item and select the words that are irrelevant for all categories as neutral words. We extract the words around the selected neutral word and use it to generate the term-document matrix. The neutral word itself starts with the idea that the stock movement is less related to the existence of the neutral words, and that the surrounding words of the neutral word are more likely to affect the stock price movements. And apply it to the algorithm that classifies the stock price fluctuations with the generated term-document matrix. In this study, we firstly removed stop words and selected neutral words for each stock. And we used a method to exclude words that are included in news articles for other stocks among the selected words. Through the online news portal, we collected four months of news articles on the top 10 market cap stocks. We split the news articles into 3 month news data as training data and apply the remaining one month news articles to the model to predict the stock price movements of the next day. We used SVM, Boosting and Random Forest for building models and predicting the movements of stock prices. The stock market opened for four months (2016/02/01 ~ 2016/05/31) for a total of 80 days, using the initial 60 days as a training set and the remaining 20 days as a test set. The proposed word - based algorithm in this study showed better classification performance than the word selection method based on sparsity. This study predicted stock price volatility by collecting and analyzing news articles of the top 10 stocks in market cap. We used the term - document matrix based classification model to estimate the stock price fluctuations and compared the performance of the existing sparse - based word extraction method and the suggested method of removing words from the term - document matrix. The suggested method differs from the word extraction method in that it uses not only the news articles for the corresponding stock but also other news items to determine the words to extract. In other words, it removed not only the words that appeared in all the increase and decrease but also the words that appeared common in the news for other stocks. When the prediction accuracy was compared, the suggested method showed higher accuracy. The limitation of this study is that the stock price prediction was set up to classify the rise and fall, and the experiment was conducted only for the top ten stocks. The 10 stocks used in the experiment do not represent the entire stock market. In addition, it is difficult to show the investment performance because stock price fluctuation and profit rate may be different. Therefore, it is necessary to study the research using more stocks and the yield prediction through trading simulation.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.

• Journal of Technology Innovation
• /
• v.17 no.1
• /
• pp.1-48
• /
• 2009

Recently we have found some symptoms that R&D fiscal incentives might not work well what it has intended through the analysis of current statistics of firm's R&D data. Firstly, we found that the growth rate of R&D investment in private sector during the recent decade has been slowdown. The average of growth rate (real value) of R&D investment is 7.1% from 1998 to 2005, while it was 13.9% from 1980 to 1997. Secondly, the relative share of R&D investment of SME has been decreased to 21%('05) from 29%('01), even though the tax credit for SME has been more beneficial than large size firm, Thirdly, The R&D expenditure of large size firms (besides 3 leading firms) has not been increased since late of 1990s. We need to find some evidence whether fiscal incentives are effective in increasing firm's R&D investment. To analyse econometric model we use firm level unbalanced panel data for 4 years (from 2002 to 2005) derived from MOST database compiled from the annual survey, "Report on the Survey of Research and Development in Science and Technology". Also we use fixed effect model (Hausman test results accept fixed effect model with 1% of significant level) and estimate the model for all firms, large firms and SME respectively. We have following results from the analysis of econometric model. For large firm: i ) R&D investment responds elastically (1.20) to sales volume. ii) government R&D subsidy induces R&D investment (0.03) not so effectively. iii) Tax price elasticity is almost unity (-0.99). iv) For large firm tax incentive is more effective than R&D subsidy For SME: i ) Sales volume increase R&D investment of SME (0.043) not so effectively. ii ) government R&D subsidy is crowding out R&D investment of SME not seriously (-0.0079) iii) Tax price elasticity is very inelastic (-0.054) To compare with other studies, Koga(2003) has a similar result of tax price elasticity for Japanese firm (-1.0036), Hall((l992) has a unit tax price elasticity, Bloom et al. (2002) has $-0.354{\sim}-0.124$ in the short run. From the results of our analysis we recommend that government R&D subsidy has to focus on such an areas like basic research and public sector (defense, energy, health etc.) not overlapped private R&D sector. For SME government has to focus on establishing R&D infrastructure. To promote tax incentive policy, we need to strengthen the tax incentive scheme for large size firm's R&D investment. We recommend tax credit for large size film be extended to total volume of R&D investment.