• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.161-177
• /
• 2015

With the rapid evolution of technology, the size, number, and the type of databases has increased concomitantly, so data mining approaches face many challenging applications from databases. One such application is discovery of fraud patterns from agricultural product wholesale transaction instances. The agricultural product wholesale market in Korea is huge, and vast numbers of transactions have been made every day. The demand for agricultural products continues to grow, and the use of electronic auction systems raises the efficiency of operations of wholesale market. Certainly, the number of unusual transactions is also assumed to be increased in proportion to the trading amount, where an unusual transaction is often the first sign of fraud. However, it is very difficult to identify and detect these transactions and the corresponding fraud occurred in agricultural product wholesale market because the types of fraud are more intelligent than ever before. The fraud can be detected by verifying the overall transaction records manually, but it requires significant amount of human resources, and ultimately is not a practical approach. Frauds also can be revealed by victim's report or complaint. But there are usually no victims in the agricultural product wholesale frauds because they are committed by collusion of an auction company and an intermediary wholesaler. Nevertheless, it is required to monitor transaction records continuously and to make an effort to prevent any fraud, because the fraud not only disturbs the fair trade order of the market but also reduces the credibility of the market rapidly. Applying data mining to such an environment is very useful since it can discover unknown fraud patterns or features from a large volume of transaction data properly. The objective of this research is to empirically investigate the factors necessary to detect fraud transactions in an agricultural product wholesale market by developing a data mining based fraud detection model. One of major frauds is the phantom transaction, which is a colluding transaction by the seller(auction company or forwarder) and buyer(intermediary wholesaler) to commit the fraud transaction. They pretend to fulfill the transaction by recording false data in the online transaction processing system without actually selling products, and the seller receives money from the buyer. This leads to the overstatement of sales performance and illegal money transfers, which reduces the credibility of market. This paper reviews the environment of wholesale market such as types of transactions, roles of participants of the market, and various types and characteristics of frauds, and introduces the whole process of developing the phantom transaction detection model. The process consists of the following 4 modules: (1) Data cleaning and standardization (2) Statistical data analysis such as distribution and correlation analysis, (3) Construction of classification model using decision-tree induction approach, (4) Verification of the model in terms of hit ratio. We collected real data from 6 associations of agricultural producers in metropolitan markets. Final model with a decision-tree induction approach revealed that monthly average trading price of item offered by forwarders is a key variable in detecting the phantom transaction. The verification procedure also confirmed the suitability of the results. However, even though the performance of the results of this research is satisfactory, sensitive issues are still remained for improving classification accuracy and conciseness of rules. One such issue is the robustness of data mining model. Data mining is very much data-oriented, so data mining models tend to be very sensitive to changes of data or situations. Thus, it is evident that this non-robustness of data mining model requires continuous remodeling as data or situation changes. We hope that this paper suggest valuable guideline to organizations and companies that consider introducing or constructing a fraud detection model in the future.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.131-145
• /
• 2020

In line with the trend of industrial innovation, IoT technology utilized in a variety of fields is emerging as a key element in creation of new business models and the provision of user-friendly services through the combination of big data. The accumulated data from devices with the Internet-of-Things (IoT) is being used in many ways to build a convenience-based smart system as it can provide customized intelligent systems through user environment and pattern analysis. Recently, it has been applied to innovation in the public domain and has been using it for smart city and smart transportation, such as solving traffic and crime problems using CCTV. In particular, it is necessary to comprehensively consider the easiness of securing real-time service data and the stability of security when planning underground services or establishing movement amount control information system to enhance citizens' or commuters' convenience in circumstances with the congestion of public transportation such as subways, urban railways, etc. However, previous studies that utilize image data have limitations in reducing the performance of object detection under private issue and abnormal conditions. The IoT device-based sensor data used in this study is free from private issue because it does not require identification for individuals, and can be effectively utilized to build intelligent public services for unspecified people. Especially, sensor data stored by the IoT device need not be identified to an individual, and can be effectively utilized for constructing intelligent public services for many and unspecified people as data free form private issue. We utilize the IoT-based infrared sensor devices for an intelligent pedestrian tracking system in metro service which many people use on a daily basis and temperature data measured by sensors are therein transmitted in real time. The experimental environment for collecting data detected in real time from sensors was established for the equally-spaced midpoints of 4×4 upper parts in the ceiling of subway entrances where the actual movement amount of passengers is high, and it measured the temperature change for objects entering and leaving the detection spots. The measured data have gone through a preprocessing in which the reference values for 16 different areas are set and the difference values between the temperatures in 16 distinct areas and their reference values per unit of time are calculated. This corresponds to the methodology that maximizes movement within the detection area. In addition, the size of the data was increased by 10 times in order to more sensitively reflect the difference in temperature by area. For example, if the temperature data collected from the sensor at a given time were 28.5℃, the data analysis was conducted by changing the value to 285. As above, the data collected from sensors have the characteristics of time series data and image data with 4×4 resolution. Reflecting the characteristics of the measured, preprocessed data, we finally propose a hybrid algorithm that combines CNN in superior performance for image classification and LSTM, especially suitable for analyzing time series data, as referred to CNN-LSTM (Convolutional Neural Network-Long Short Term Memory). In the study, the CNN-LSTM algorithm is used to predict the number of passing persons in one of 4×4 detection areas. We verified the validation of the proposed model by taking performance comparison with other artificial intelligence algorithms such as Multi-Layer Perceptron (MLP), Long Short Term Memory (LSTM) and RNN-LSTM (Recurrent Neural Network-Long Short Term Memory). As a result of the experiment, proposed CNN-LSTM hybrid model compared to MLP, LSTM and RNN-LSTM has the best predictive performance. By utilizing the proposed devices and models, it is expected various metro services will be provided with no illegal issue about the personal information such as real-time monitoring of public transport facilities and emergency situation response services on the basis of congestion. However, the data have been collected by selecting one side of the entrances as the subject of analysis, and the data collected for a short period of time have been applied to the prediction. There exists the limitation that the verification of application in other environments needs to be carried out. In the future, it is expected that more reliability will be provided for the proposed model if experimental data is sufficiently collected in various environments or if learning data is further configured by measuring data in other sensors.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.139-157
• /
• 2016

Bankruptcy involves considerable costs, so it can have significant effects on a country's economy. Thus, bankruptcy prediction is an important issue. Over the past several decades, many researchers have addressed topics associated with bankruptcy prediction. Early research on bankruptcy prediction employed conventional statistical methods such as univariate analysis, discriminant analysis, multiple regression, and logistic regression. Later on, many studies began utilizing artificial intelligence techniques such as inductive learning, neural networks, and case-based reasoning. Currently, ensemble models are being utilized to enhance the accuracy of bankruptcy prediction. Ensemble classification involves combining multiple classifiers to obtain more accurate predictions than those obtained using individual models. Ensemble learning techniques are known to be very useful for improving the generalization ability of the classifier. Base classifiers in the ensemble must be as accurate and diverse as possible in order to enhance the generalization ability of an ensemble model. Commonly used methods for constructing ensemble classifiers include bagging, boosting, and random subspace. The random subspace method selects a random feature subset for each classifier from the original feature space to diversify the base classifiers of an ensemble. Each ensemble member is trained by a randomly chosen feature subspace from the original feature set, and predictions from each ensemble member are combined by an aggregation method. The k-nearest neighbors (KNN) classifier is robust with respect to variations in the dataset but is very sensitive to changes in the feature space. For this reason, KNN is a good classifier for the random subspace method. The KNN random subspace ensemble model has been shown to be very effective for improving an individual KNN model. The k parameter of KNN base classifiers and selected feature subsets for base classifiers play an important role in determining the performance of the KNN ensemble model. However, few studies have focused on optimizing the k parameter and feature subsets of base classifiers in the ensemble. This study proposed a new ensemble method that improves upon the performance KNN ensemble model by optimizing both k parameters and feature subsets of base classifiers. A genetic algorithm was used to optimize the KNN ensemble model and improve the prediction accuracy of the ensemble model. The proposed model was applied to a bankruptcy prediction problem by using a real dataset from Korean companies. The research data included 1800 externally non-audited firms that filed for bankruptcy (900 cases) or non-bankruptcy (900 cases). Initially, the dataset consisted of 134 financial ratios. Prior to the experiments, 75 financial ratios were selected based on an independent sample t-test of each financial ratio as an input variable and bankruptcy or non-bankruptcy as an output variable. Of these, 24 financial ratios were selected by using a logistic regression backward feature selection method. The complete dataset was separated into two parts: training and validation. The training dataset was further divided into two portions: one for the training model and the other to avoid overfitting. The prediction accuracy against this dataset was used to determine the fitness value in order to avoid overfitting. The validation dataset was used to evaluate the effectiveness of the final model. A 10-fold cross-validation was implemented to compare the performances of the proposed model and other models. To evaluate the effectiveness of the proposed model, the classification accuracy of the proposed model was compared with that of other models. The Q-statistic values and average classification accuracies of base classifiers were investigated. The experimental results showed that the proposed model outperformed other models, such as the single model and random subspace ensemble model.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.139-160
• /
• 2017

Technology commercialization creates effective economic value by linking the company's R & D processes and outputs to the market. This technology commercialization is important in that a company can retain and maintain a sustained competitive advantage. In order for a specific technology to be commercialized, it goes through the stage of technical planning, technology research and development, and commercialization. This process involves a lot of time and money. Therefore, the duration and cost of technology commercialization are important decision information for determining the market entry strategy. In addition, it is more important information for a technology investor to rationally evaluate the technology value. In this way, it is very important to scientifically estimate the duration and cost of the technology commercialization. However, research on technology commercialization is insufficient and related methodology are lacking. In this study, we propose an evaluation model that can estimate the duration and cost of R & D technology commercialization for small and medium-sized enterprises. To accomplish this, this study collected the public data of the National Science & Technology Information Service (NTIS) and the survey data provided by the Small and Medium Business Administration. Also this study will develop the estimation model of commercialization duration and cost of R&D performance on using these data based on the market approach, one of the technology valuation methods. Specifically, this study defined the process of commercialization as consisting of development planning, development progress, and commercialization. We collected the data from the NTIS database and the survey of SMEs technical statistics of the Small and Medium Business Administration. We derived the key variables such as stage-wise R&D costs and duration, the factors of the technology itself, the factors of the technology development, and the environmental factors. At first, given data, we estimates the costs and duration in each technology readiness level (basic research, applied research, development research, prototype production, commercialization), for each industry classification. Then, we developed and verified the research model of each industry classification. The results of this study can be summarized as follows. Firstly, it is reflected in the technology valuation model and can be used to estimate the objective economic value of technology. The duration and the cost from the technology development stage to the commercialization stage is a critical factor that has a great influence on the amount of money to discount the future sales from the technology. The results of this study can contribute to more reliable technology valuation because it estimates the commercialization duration and cost scientifically based on past data. Secondly, we have verified models of various fields such as statistical model and data mining model. The statistical model helps us to find the important factors to estimate the duration and cost of technology Commercialization, and the data mining model gives us the rules or algorithms to be applied to an advanced technology valuation system. Finally, this study reaffirms the importance of commercialization costs and durations, which has not been actively studied in previous studies. The results confirm the significant factors to affect the commercialization costs and duration, furthermore the factors are different depending on industry classification. Practically, the results of this study can be reflected in the technology valuation system, which can be provided by national research institutes and R & D staff to provide sophisticated technology valuation. The relevant logic or algorithm of the research result can be implemented independently so that it can be directly reflected in the system, so researchers can use it practically immediately. In conclusion, the results of this study can be a great contribution not only to the theoretical contributions but also to the practical ones.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.157-176
• /
• 2016

For a long time, mobile phone had a sole function of communication. Recently however, abrupt innovations in technology allowed extension of the sphere in mobile phone activities. Development of technology enabled realization of almost computer-like environment even on a very small device. Such advancement yielded several forms of new high-tech devices such as smartphone and tablet PC, which quickly proliferated. Simultaneously with the diffusion of the mobile devices, mobile applications for those devices also prospered and soon became deeply penetrated in consumers' daily lives. Numerous mobile applications have been released in app stores yielding trillions of cumulative downloads. However, a big majority of the applications are disregarded from consumers. Even after the applications are purchased, they do not survive long in consumers' mobile devices and are soon abandoned. Nevertheless, it is imperative for both app developers and app-store operators to understand consumer behaviors and to develop marketing strategies aiming to make sustainable business by first increasing sales of mobile applications and by also designing surviving strategy for applications. Therefore, this research analyzes consumers' mobile application usage behavior in a frame of substitution/supplementary of application categories and several explanatory variables. Considering that consumers of mobile devices use multiple apps simultaneously, this research adopts multivariate probit models to explain mobile application usage behavior and to derive correlation between categories of applications for observing substitution/supplementary of application use. The research adopts several explanatory variables including sociodemographic data, user experiences of purchased applications that reflect future purchasing behavior of paid applications as well as consumer attitudes toward marketing efforts, variables representing consumer attitudes toward rating of the app and those representing consumer attitudes toward app-store promotion efforts (i.e., top developer badge and editor's choice badge). Results of this study can be explained in hedonic and utilitarian framework. Consumers who use hedonic applications, such as those of game and entertainment-related, are of young age with low education level. However, consumers who are old and have received higher education level prefer utilitarian application category such as life, information etc. There are disputable arguments over whether the users of SNS are hedonic or utilitarian. In our results, consumers who are younger and those with higher education level prefer using SNS category applications, which is in a middle of utilitarian and hedonic results. Also, applications that are directly related to tangible assets, such as banking, stock and mobile shopping, are only negatively related to experience of purchasing of paid app, meaning that consumers who put weights on tangible assets do not prefer buying paid application. Regarding categories, most correlations among categories are significantly positive. This is because someone who spend more time on mobile devices tends to use more applications. Game and entertainment category shows significant and positive correlation; however, there exists significantly negative correlation between game and information, as well as game and e-commerce categories of applications. Meanwhile, categories of game and SNS as well as game and finance have shown no significant correlations. This result clearly shows that mobile application usage behavior is quite clearly distinguishable - that the purpose of using mobile devices are polarized into utilitarian and hedonic purpose. This research proves several arguments that can only be explained by second-hand real data, not by survey data, and offers behavioral explanations of mobile application usage in consumers' perspectives. This research also shows substitution/supplementary patterns of consumer application usage, which then explain consumers' mobile application usage behaviors. However, this research has limitations in some points. Classification of categories itself is disputable, for classification is diverged among several studies. Therefore, there is a possibility of change in results depending on the classification. Lastly, although the data are collected in an individual application level, we reduce its observation into an individual level. Further research will be done to resolve these limitations.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.1-17
• /
• 2019

Because stock price forecasting is an important issue both academically and practically, research in stock price prediction has been actively conducted. The stock price forecasting research is classified into using structured data and using unstructured data. With structured data such as historical stock price and financial statements, past studies usually used technical analysis approach and fundamental analysis. In the big data era, the amount of information has rapidly increased, and the artificial intelligence methodology that can find meaning by quantifying string information, which is an unstructured data that takes up a large amount of information, has developed rapidly. With these developments, many attempts with unstructured data are being made to predict stock prices through online news by applying text mining to stock price forecasts. The stock price prediction methodology adopted in many papers is to forecast stock prices with the news of the target companies to be forecasted. However, according to previous research, not only news of a target company affects its stock price, but news of companies that are related to the company can also affect the stock price. However, finding a highly relevant company is not easy because of the market-wide impact and random signs. Thus, existing studies have found highly relevant companies based primarily on pre-determined international industry classification standards. However, according to recent research, global industry classification standard has different homogeneity within the sectors, and it leads to a limitation that forecasting stock prices by taking them all together without considering only relevant companies can adversely affect predictive performance. To overcome the limitation, we first used random matrix theory with text mining for stock prediction. Wherever the dimension of data is large, the classical limit theorems are no longer suitable, because the statistical efficiency will be reduced. Therefore, a simple correlation analysis in the financial market does not mean the true correlation. To solve the issue, we adopt random matrix theory, which is mainly used in econophysics, to remove market-wide effects and random signals and find a true correlation between companies. With the true correlation, we perform cluster analysis to find relevant companies. Also, based on the clustering analysis, we used multiple kernel learning algorithm, which is an ensemble of support vector machine to incorporate the effects of the target firm and its relevant firms simultaneously. Each kernel was assigned to predict stock prices with features of financial news of the target firm and its relevant firms. The results of this study are as follows. The results of this paper are as follows. (1) Following the existing research flow, we confirmed that it is an effective way to forecast stock prices using news from relevant companies. (2) When looking for a relevant company, looking for it in the wrong way can lower AI prediction performance. (3) The proposed approach with random matrix theory shows better performance than previous studies if cluster analysis is performed based on the true correlation by removing market-wide effects and random signals. The contribution of this study is as follows. First, this study shows that random matrix theory, which is used mainly in economic physics, can be combined with artificial intelligence to produce good methodologies. This suggests that it is important not only to develop AI algorithms but also to adopt physics theory. This extends the existing research that presented the methodology by integrating artificial intelligence with complex system theory through transfer entropy. Second, this study stressed that finding the right companies in the stock market is an important issue. This suggests that it is not only important to study artificial intelligence algorithms, but how to theoretically adjust the input values. Third, we confirmed that firms classified as Global Industrial Classification Standard (GICS) might have low relevance and suggested it is necessary to theoretically define the relevance rather than simply finding it in the GICS.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.251-273
• /
• 2022

Recently, research on applying text analysis to deep learning has steadily continued. In particular, researches have been actively conducted to understand the meaning of words and perform tasks such as summarization and sentiment classification through a pre-trained language model that learns large datasets. However, existing pre-trained language models show limitations in that they do not understand specific domains well. Therefore, in recent years, the flow of research has shifted toward creating a language model specialized for a particular domain. Domain-specific pre-trained language models allow the model to understand the knowledge of a particular domain better and reveal performance improvements on various tasks in the field. However, domain-specific further pre-training is expensive to acquire corpus data of the target domain. Furthermore, many cases have reported that performance improvement after further pre-training is insignificant in some domains. As such, it is difficult to decide to develop a domain-specific pre-trained language model, while it is not clear whether the performance will be improved dramatically. In this paper, we present a way to proactively check the expected performance improvement by further pre-training in a domain before actually performing further pre-training. Specifically, after selecting three domains, we measured the increase in classification accuracy through further pre-training in each domain. We also developed and presented new indicators to estimate the specificity of the domain based on the normalized frequency of the keywords used in each domain. Finally, we conducted classification using a pre-trained language model and a domain-specific pre-trained language model of three domains. As a result, we confirmed that the higher the domain specificity index, the higher the performance improvement through further pre-training.

• 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.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.