• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.71-90
• /
• 2020

Recently, the global insurance industry is rapidly developing digital transformation through the use of artificial intelligence technologies such as machine learning, natural language processing, and deep learning. As a result, more and more foreign insurers have achieved the success of artificial intelligence technology-based InsurTech and platform business, and Ping An Insurance Group Ltd., China's largest private company, is leading China's global fourth industrial revolution with remarkable achievements in InsurTech and Digital Platform as a result of its constant innovation, using 'finance and technology' and 'finance and ecosystem' as keywords for companies. In response, this study analyzed the InsurTech and platform business activities of Ping An Insurance Group Ltd. through the ser-M analysis model to provide strategic implications for revitalizing AI technology-based businesses of domestic insurers. The ser-M analysis model has been studied so that the vision and leadership of the CEO, the historical environment of the enterprise, the utilization of various resources, and the unique mechanism relationships can be interpreted in an integrated manner as a frame that can be interpreted in terms of the subject, environment, resource and mechanism. As a result of the case analysis, Ping An Insurance Group Ltd. has achieved cost reduction and customer service development by digitally innovating its entire business area such as sales, underwriting, claims, and loan service by utilizing core artificial intelligence technologies such as facial, voice, and facial expression recognition. In addition, "online data in China" and "the vast offline data and insights accumulated by the company" were combined with new technologies such as artificial intelligence and big data analysis to build a digital platform that integrates financial services and digital service businesses. Ping An Insurance Group Ltd. challenged constant innovation, and as of 2019, sales reached $155 billion, ranking seventh among all companies in the Global 2000 rankings selected by Forbes Magazine. Analyzing the background of the success of Ping An Insurance Group Ltd. from the perspective of ser-M, founder Mammingz quickly captured the development of digital technology, market competition and changes in population structure in the era of the fourth industrial revolution, and established a new vision and displayed an agile leadership of digital technology-focused. Based on the strong leadership led by the founder in response to environmental changes, the company has successfully led InsurTech and Platform Business through innovation of internal resources such as investment in artificial intelligence technology, securing excellent professionals, and strengthening big data capabilities, combining external absorption capabilities, and strategic alliances among various industries. Through this success story analysis of Ping An Insurance Group Ltd., the following implications can be given to domestic insurance companies that are preparing for digital transformation. First, CEOs of domestic companies also need to recognize the paradigm shift in industry due to the change in digital technology and quickly arm themselves with digital technology-oriented leadership to spearhead the digital transformation of enterprises. Second, the Korean government should urgently overhaul related laws and systems to further promote the use of data between different industries and provide drastic support such as deregulation, tax benefits and platform provision to help the domestic insurance industry secure global competitiveness. Third, Korean companies also need to make bolder investments in the development of artificial intelligence technology so that systematic securing of internal and external data, training of technical personnel, and patent applications can be expanded, and digital platforms should be quickly established so that diverse customer experiences can be integrated through learned artificial intelligence technology. Finally, since there may be limitations to generalization through a single case of an overseas insurance company, I hope that in the future, more extensive research will be conducted on various management strategies related to artificial intelligence technology by analyzing cases of multiple industries or multiple companies or conducting empirical research.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.89-105
• /
• 2014

After emergence of Internet, social media with highly interactive Web 2.0 applications has provided very user friendly means for consumers and companies to communicate with each other. Users have routinely published contents involving their opinions and interests in social media such as blogs, forums, chatting rooms, and discussion boards, and the contents are released real-time in the Internet. For that reason, many researchers and marketers regard social media contents as the source of information for business analytics to develop business insights, and many studies have reported results on mining business intelligence from Social media content. In particular, opinion mining and sentiment analysis, as a technique to extract, classify, understand, and assess the opinions implicit in text contents, are frequently applied into social media content analysis because it emphasizes determining sentiment polarity and extracting authors' opinions. A number of frameworks, methods, techniques and tools have been presented by these researchers. However, we have found some weaknesses from their methods which are often technically complicated and are not sufficiently user-friendly for helping business decisions and planning. In this study, we attempted to formulate a more comprehensive and practical approach to conduct opinion mining with visual deliverables. First, we described the entire cycle of practical opinion mining using Social media content from the initial data gathering stage to the final presentation session. Our proposed approach to opinion mining consists of four phases: collecting, qualifying, analyzing, and visualizing. In the first phase, analysts have to choose target social media. Each target media requires different ways for analysts to gain access. There are open-API, searching tools, DB2DB interface, purchasing contents, and so son. Second phase is pre-processing to generate useful materials for meaningful analysis. If we do not remove garbage data, results of social media analysis will not provide meaningful and useful business insights. To clean social media data, natural language processing techniques should be applied. The next step is the opinion mining phase where the cleansed social media content set is to be analyzed. The qualified data set includes not only user-generated contents but also content identification information such as creation date, author name, user id, content id, hit counts, review or reply, favorite, etc. Depending on the purpose of the analysis, researchers or data analysts can select a suitable mining tool. Topic extraction and buzz analysis are usually related to market trends analysis, while sentiment analysis is utilized to conduct reputation analysis. There are also various applications, such as stock prediction, product recommendation, sales forecasting, and so on. The last phase is visualization and presentation of analysis results. The major focus and purpose of this phase are to explain results of analysis and help users to comprehend its meaning. Therefore, to the extent possible, deliverables from this phase should be made simple, clear and easy to understand, rather than complex and flashy. To illustrate our approach, we conducted a case study on a leading Korean instant noodle company. We targeted the leading company, NS Food, with 66.5% of market share; the firm has kept No. 1 position in the Korean "Ramen" business for several decades. We collected a total of 11,869 pieces of contents including blogs, forum contents and news articles. After collecting social media content data, we generated instant noodle business specific language resources for data manipulation and analysis using natural language processing. In addition, we tried to classify contents in more detail categories such as marketing features, environment, reputation, etc. In those phase, we used free ware software programs such as TM, KoNLP, ggplot2 and plyr packages in R project. As the result, we presented several useful visualization outputs like domain specific lexicons, volume and sentiment graphs, topic word cloud, heat maps, valence tree map, and other visualized images to provide vivid, full-colored examples using open library software packages of the R project. Business actors can quickly detect areas by a swift glance that are weak, strong, positive, negative, quiet or loud. Heat map is able to explain movement of sentiment or volume in categories and time matrix which shows density of color on time periods. Valence tree map, one of the most comprehensive and holistic visualization models, should be very helpful for analysts and decision makers to quickly understand the "big picture" business situation with a hierarchical structure since tree-map can present buzz volume and sentiment with a visualized result in a certain period. This case study offers real-world business insights from market sensing which would demonstrate to practical-minded business users how they can use these types of results for timely decision making in response to on-going changes in the market. We believe our approach can provide practical and reliable guide to opinion mining with visualized results that are immediately useful, not just in food industry but in other industries as well.

• Korean Journal of Soil Science and Fertilizer
• /
• v.6 no.1
• /
• pp.35-52
• /
• 1973

Red Yellow Soils occur very commonly in Korea and constitute the important upland soils of the country which are either presently being cultivated or are suitable for reclaiming and cultivating. These soils are distributed on rolling, moutain foot slopes, and terraces in the southern and western parts of the central districts of Korea, and are derived from granite, granite gneiss, old alluvium and locally from limestone and shale. This report is a summary of the morphology, physical and chemical characteristics of Red Yellow Soils. The data obtained from detailed soil surveys since 1964 are summarized as follows. 1. Red-Yellows Soils have an A, Bt, C profile. The A horizon is dark colored coarse loamy or fine loamy with the thin layer of organic matter. The B horizon is dominantly strong brown, reddish brown or yellowish red, clayey or fine loamy with clay cutans on the soil peds. The C horizon varies with parent materials, and is coarser texture and has a less developed structure than the Bt horizon. Soil depth, varied with relief and parent materials, is predominantly around 100cm. 2. In the physical characteristics, the clay content of surface soil is 18 to 35 percent, and of subsoil is 30 to 90 percent nearly two times higher than the surface soil. Bulk density is 1.2 to 1.3 in the surface soil and 1.3 to 1.5 in the subsoil. The range of 3-phase is mostly narrow with 45 to 50 percent in solid phase, 30 to 45 percent in liquid one, and 5 to 25 percent in gaseous state in the surface soil; and 50 to 60 solid, 35 to 45 percent liquid and less than 15 percent gaseous in the subsoil. Available soil moisture capacity ranges from 10 to 23 percent in the surface soil, and 5 to 16 percent in the subsoil. 3. Chemically, soil reaction is neutral to alkaline in soils derived from limestone or old fluviomarine deposits, and acid to strong acid in other ones. The organic matter content of surface soil varying considerably with vegetation, erosion and cultivation, ranges from 1.0 to 5.0 percent. The cation exchange capacity is 5 to 40 me/100gr soil and closely related to the content of organic matter, clay and silt. Base saturation is low, on the whole, due to the leaching of extractable cations, but is high in soils derived from limestone with high content of lime and magnesium. 4. Most of these soils mainly contain halloysite (a part of kaolin minerals), vermiculite (weathered mica), and illite, including small amount of chlorite, gibbsite, hematite, quartz and feldspar. 5. Characteristically they are similar to Red Yellow Podzolic Soils and a part of Reddish Brown Lateritic Soils of the United States, and Red Yellow Soils of Japan. According to USDA 7th Approximation, they can be classified as Udu Its or Udalfs, and in FAO classification system to Acrisols, Luvisols, and Nitosols.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.32 no.4
• /
• pp.14-23
• /
• 2014

The purpose of this study is to contribute in building credibility of the methodology of the appearance of the traditional colors and the interpretation of the meaning of those appearances by analyzing the spatial construction and configuration and the traditional colors that appear in spatial elements about the scenery component that appear in Seyeonjeong. We conducted a literature research about the traditional colors, the background of the creation of Seyeonjeong, and etc. For the contents for the empirical analysis, we took the scenery and space elements in the poems, such as Eobusasisa and O-u-ga, and the contents of poems related to ojeongsaek (five Korean traditional colors) based on the Yin-Yang and the Five Elements ideology Particularly, after dividing the spatial elements appearing in Seyoenjeong into visual, synesthetic, symbolic/cognitive spatial element, we further distinguished the visual space into positions and directions of the of the spaces and the scenery of the season; the synesthetic space into seasons, time and five senses; and the symbolic/cognitive space into chiljeong (or the seven passions) and sadan (or the four clues). Then we carried out the study by analyzing the correlation between the intention of the garden creation and the meaning of the spaces, through the analysis of ojeongsaek system for each spatial element. Firstly, spatial structure and format that appear in Seyeonjeong can be divided into two directional axes of southeast and northwest according to the flat form of the Seyeongjeong's rectangular palace, with Seyeongjoeng as the center. Secondly, in spatial component element, the frequencies of appearance of the traditional colors of Seyoenjeong are 33.2% for white, 20.8% for blue, 20.8% for black, 18.7% for red and 6.3% for yellow. Thirdly, based on the analysis of the traditional colors the most frequent appearance of 'white' left a room for interpretation like the creation of Seyeonjeong was to enjoy secular living without lingering political feelings so that the high mountains remain clear and clean. Also, the predominant frequency of appearance of blue, similar frequency of appearance of black and red, and the least frequent appearance of yellow is in agreement with or can be at least interpreted related to Yun Seon-do's intention for creating Seyeonjeong not for political rank or power but as a place to enjoy nature, through which he can build on his knowledge, and to lead rest of his life as a noble being through plays, like dancing and writing poems. Fourthly, these interpretations of the analysis of the frequency of appearance of the traditional colors of Seyeongjong shows the reliability, validity, and consistency of the methodology of the analysis of the frequency of appearance of the traditional colors and the interpretation of the meanings in the context that the color white appears most frequently in Soswewon as well and that the background life of the Soswewon's creator Yangsanbo can be interpreted in a similarly way. Above all, this study is significant from the fact that we proposed a theory about the method of analysis and interpretation of the traditional colors in a traditional landscape space. Moreover, there is a great significance of discovering that traditional colors appear in traditional spaces and this can be used as a methodological framework to interpret things like, intention for creation of (buildings/architectures).

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.101-123
• /
• 2013

Recently due to the advancements of science and information technology, the socio-economic business areas are changing from the industrial economy to a knowledge economy. Furthermore, companies need to do creation of new value through continuous innovation, development of core competencies and technologies, and technological convergence. Therefore, the identification of major trends in technology research and the interdisciplinary knowledge-based prediction of integrated technologies and promising techniques are required for firms to gain and sustain competitive advantage and future growth engines. The aim of this paper is to understand the recent research trend in management of technology (MOT) and to foresee promising technologies with deep knowledge for both technology and business. Furthermore, this study intends to give a clear way to find new technical value for constant innovation and to capture core technology and technology convergence. Bibliometrics is a metrical analysis to understand literature's characteristics. Traditional bibliometrics has its limitation not to understand relationship between trend in technology management and technology itself, since it focuses on quantitative indices such as quotation frequency. To overcome this issue, the network focused bibliometrics has been used instead of traditional one. The network focused bibliometrics mainly uses "Co-citation" and "Co-word" analysis. In this study, a keywords network analysis, one of social network analysis, is performed to analyze recent research trend in MOT. For the analysis, we collected keywords from research papers published in international journals related MOT between 2002 and 2011, constructed a keyword network, and then conducted the keywords network analysis. Over the past 40 years, the studies in social network have attempted to understand the social interactions through the network structure represented by connection patterns. In other words, social network analysis has been used to explain the structures and behaviors of various social formations such as teams, organizations, and industries. In general, the social network analysis uses data as a form of matrix. In our context, the matrix depicts the relations between rows as papers and columns as keywords, where the relations are represented as binary. Even though there are no direct relations between papers who have been published, the relations between papers can be derived artificially as in the paper-keyword matrix, in which each cell has 1 for including or 0 for not including. For example, a keywords network can be configured in a way to connect the papers which have included one or more same keywords. After constructing a keywords network, we analyzed frequency of keywords, structural characteristics of keywords network, preferential attachment and growth of new keywords, component, and centrality. The results of this study are as follows. First, a paper has 4.574 keywords on the average. 90% of keywords were used three or less times for past 10 years and about 75% of keywords appeared only one time. Second, the keyword network in MOT is a small world network and a scale free network in which a small number of keywords have a tendency to become a monopoly. Third, the gap between the rich (with more edges) and the poor (with fewer edges) in the network is getting bigger as time goes on. Fourth, most of newly entering keywords become poor nodes within about 2~3 years. Finally, keywords with high degree centrality, betweenness centrality, and closeness centrality are "Innovation," "R&D," "Patent," "Forecast," "Technology transfer," "Technology," and "SME". The results of analysis will help researchers identify major trends in MOT research and then seek a new research topic. We hope that the result of the analysis will help researchers of MOT identify major trends in technology research, and utilize as useful reference information when they seek consilience with other fields of study and select a new research topic.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.119-133
• /
• 2020

Fama asserted that in an efficient market, we can't make a trading rule that consistently outperforms the average stock market returns. This study aims to suggest a machine learning algorithm to improve the trading performance of an intraday short volatility strategy applying asymmetric volatility spillover effect, and analyze its trading performance improvement. Generally stock market volatility has a negative relation with stock market return and the Korean stock market volatility is influenced by the US stock market volatility. This volatility spillover effect is asymmetric. The asymmetric volatility spillover effect refers to the phenomenon that the US stock market volatility up and down differently influence the next day's volatility of the Korean stock market. We collected the S&P 500 index, VIX, KOSPI 200 index, and V-KOSPI 200 from 2008 to 2018. We found the negative relation between the S&P 500 and VIX, and the KOSPI 200 and V-KOSPI 200. We also documented the strong volatility spillover effect from the VIX to the V-KOSPI 200. Interestingly, the asymmetric volatility spillover was also found. Whereas the VIX up is fully reflected in the opening volatility of the V-KOSPI 200, the VIX down influences partially in the opening volatility and its influence lasts to the Korean market close. If the stock market is efficient, there is no reason why there exists the asymmetric volatility spillover effect. It is a counter example of the efficient market hypothesis. To utilize this type of anomalous volatility spillover pattern, we analyzed the intraday volatility selling strategy. This strategy sells short the Korean volatility market in the morning after the US stock market volatility closes down and takes no position in the volatility market after the VIX closes up. It produced profit every year between 2008 and 2018 and the percent profitable is 68%. The trading performance showed the higher average annual return of 129% relative to the benchmark average annual return of 33%. The maximum draw down, MDD, is -41%, which is lower than that of benchmark -101%. The Sharpe ratio 0.32 of SVS strategy is much greater than the Sharpe ratio 0.08 of the Benchmark strategy. The Sharpe ratio simultaneously considers return and risk and is calculated as return divided by risk. Therefore, high Sharpe ratio means high performance when comparing different strategies with different risk and return structure. Real world trading gives rise to the trading costs including brokerage cost and slippage cost. When the trading cost is considered, the performance difference between 76% and -10% average annual returns becomes clear. To improve the performance of the suggested volatility trading strategy, we used the well-known SVM algorithm. Input variables include the VIX close to close return at day t-1, the VIX open to close return at day t-1, the VK open return at day t, and output is the up and down classification of the VK open to close return at day t. The training period is from 2008 to 2014 and the testing period is from 2015 to 2018. The kernel functions are linear function, radial basis function, and polynomial function. We suggested the modified-short volatility strategy that sells the VK in the morning when the SVM output is Down and takes no position when the SVM output is Up. The trading performance was remarkably improved. The 5-year testing period trading results of the m-SVS strategy showed very high profit and low risk relative to the benchmark SVS strategy. The annual return of the m-SVS strategy is 123% and it is higher than that of SVS strategy. The risk factor, MDD, was also significantly improved from -41% to -29%.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.59-77
• /
• 2012

This study focuses on predicting which firms will increase capital by issuing new stocks in the near future. Many stakeholders, including banks, credit rating agencies and investors, performs a variety of analyses for firms' growth, profitability, stability, activity, productivity, etc., and regularly report the firms' financial analysis indices. In the paper, we develop predictive models for rights issues using these financial analysis indices and data mining techniques. This study approaches to building the predictive models from the perspective of two different analyses. The first is the analysis period. We divide the analysis period into before and after the IMF financial crisis, and examine whether there is the difference between the two periods. The second is the prediction time. In order to predict when firms increase capital by issuing new stocks, the prediction time is categorized as one year, two years and three years later. Therefore Total six prediction models are developed and analyzed. In this paper, we employ the decision tree technique to build the prediction models for rights issues. The decision tree is the most widely used prediction method which builds decision trees to label or categorize cases into a set of known classes. In contrast to neural networks, logistic regression and SVM, decision tree techniques are well suited for high-dimensional applications and have strong explanation capabilities. There are well-known decision tree induction algorithms such as CHAID, CART, QUEST, C5.0, etc. Among them, we use C5.0 algorithm which is the most recently developed algorithm and yields performance better than other algorithms. We obtained data for the rights issue and financial analysis from TS2000 of Korea Listed Companies Association. A record of financial analysis data is consisted of 89 variables which include 9 growth indices, 30 profitability indices, 23 stability indices, 6 activity indices and 8 productivity indices. For the model building and test, we used 10,925 financial analysis data of total 658 listed firms. PASW Modeler 13 was used to build C5.0 decision trees for the six prediction models. Total 84 variables among financial analysis data are selected as the input variables of each model, and the rights issue status (issued or not issued) is defined as the output variable. To develop prediction models using C5.0 node (Node Options: Output type = Rule set, Use boosting = false, Cross-validate = false, Mode = Simple, Favor = Generality), we used 60% of data for model building and 40% of data for model test. The results of experimental analysis show that the prediction accuracies of data after the IMF financial crisis (59.04% to 60.43%) are about 10 percent higher than ones before IMF financial crisis (68.78% to 71.41%). These results indicate that since the IMF financial crisis, the reliability of financial analysis indices has increased and the firm intention of rights issue has been more obvious. The experiment results also show that the stability-related indices have a major impact on conducting rights issue in the case of short-term prediction. On the other hand, the long-term prediction of conducting rights issue is affected by financial analysis indices on profitability, stability, activity and productivity. All the prediction models include the industry code as one of significant variables. This means that companies in different types of industries show their different types of patterns for rights issue. We conclude that it is desirable for stakeholders to take into account stability-related indices and more various financial analysis indices for short-term prediction and long-term prediction, respectively. The current study has several limitations. First, we need to compare the differences in accuracy by using different data mining techniques such as neural networks, logistic regression and SVM. Second, we are required to develop and to evaluate new prediction models including variables which research in the theory of capital structure has mentioned about the relevance to rights issue.

• 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 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.24 no.2
• /
• pp.59-83
• /
• 2018

With the increasing importance of sentiment analysis to grasp the needs of customers and the public, various types of deep learning models have been actively applied to English texts. In the sentiment analysis of English texts by deep learning, natural language sentences included in training and test datasets are usually converted into sequences of word vectors before being entered into the deep learning models. In this case, word vectors generally refer to vector representations of words obtained through splitting a sentence by space characters. There are several ways to derive word vectors, one of which is Word2Vec used for producing the 300 dimensional Google word vectors from about 100 billion words of Google News data. They have been widely used in the studies of sentiment analysis of reviews from various fields such as restaurants, movies, laptops, cameras, etc. Unlike English, morpheme plays an essential role in sentiment analysis and sentence structure analysis in Korean, which is a typical agglutinative language with developed postpositions and endings. A morpheme can be defined as the smallest meaningful unit of a language, and a word consists of one or more morphemes. For example, for a word '예쁘고', the morphemes are '예쁘(= adjective)' and '고(=connective ending)'. Reflecting the significance of Korean morphemes, it seems reasonable to adopt the morphemes as a basic unit in Korean sentiment analysis. Therefore, in this study, we use 'morpheme vector' as an input to a deep learning model rather than 'word vector' which is mainly used in English text. The morpheme vector refers to a vector representation for the morpheme and can be derived by applying an existent word vector derivation mechanism to the sentences divided into constituent morphemes. By the way, here come some questions as follows. What is the desirable range of POS(Part-Of-Speech) tags when deriving morpheme vectors for improving the classification accuracy of a deep learning model? Is it proper to apply a typical word vector model which primarily relies on the form of words to Korean with a high homonym ratio? Will the text preprocessing such as correcting spelling or spacing errors affect the classification accuracy, especially when drawing morpheme vectors from Korean product reviews with a lot of grammatical mistakes and variations? We seek to find empirical answers to these fundamental issues, which may be encountered first when applying various deep learning models to Korean texts. As a starting point, we summarized these issues as three central research questions as follows. First, which is better effective, to use morpheme vectors from grammatically correct texts of other domain than the analysis target, or to use morpheme vectors from considerably ungrammatical texts of the same domain, as the initial input of a deep learning model? Second, what is an appropriate morpheme vector derivation method for Korean regarding the range of POS tags, homonym, text preprocessing, minimum frequency? Third, can we get a satisfactory level of classification accuracy when applying deep learning to Korean sentiment analysis? As an approach to these research questions, we generate various types of morpheme vectors reflecting the research questions and then compare the classification accuracy through a non-static CNN(Convolutional Neural Network) model taking in the morpheme vectors. As for training and test datasets, Naver Shopping's 17,260 cosmetics product reviews are used. To derive morpheme vectors, we use data from the same domain as the target one and data from other domain; Naver shopping's about 2 million cosmetics product reviews and 520,000 Naver News data arguably corresponding to Google's News data. The six primary sets of morpheme vectors constructed in this study differ in terms of the following three criteria. First, they come from two types of data source; Naver news of high grammatical correctness and Naver shopping's cosmetics product reviews of low grammatical correctness. Second, they are distinguished in the degree of data preprocessing, namely, only splitting sentences or up to additional spelling and spacing corrections after sentence separation. Third, they vary concerning the form of input fed into a word vector model; whether the morphemes themselves are entered into a word vector model or with their POS tags attached. The morpheme vectors further vary depending on the consideration range of POS tags, the minimum frequency of morphemes included, and the random initialization range. All morpheme vectors are derived through CBOW(Continuous Bag-Of-Words) model with the context window 5 and the vector dimension 300. It seems that utilizing the same domain text even with a lower degree of grammatical correctness, performing spelling and spacing corrections as well as sentence splitting, and incorporating morphemes of any POS tags including incomprehensible category lead to the better classification accuracy. The POS tag attachment, which is devised for the high proportion of homonyms in Korean, and the minimum frequency standard for the morpheme to be included seem not to have any definite influence on the classification accuracy.