Feasibility of Deep Learning Algorithms for Binary Classification Problems (이진 분류문제에서의 딥러닝 알고리즘의 활용 가능성 평가)
-
- Journal of Intelligence and Information Systems
- /
- v.23 no.1
- /
- pp.95-108
- /
- 2017
Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.
Nowadays, it is common that most consumers are purchasing goods in e-stores. The e-stores eager to attract, revisit, retain, and finally convert them into loyal customers. The e-store marketers have planned and executed numerous marketing efforts. As one of the marketing activities, e-store managers attempt to build web sites that meet customers' functional and psychological needs. A wide array of studies has been done to identify factors that could affect customers' response of web sites. Majority of studies were conducted to verify technology-related and functional variables of the website which facilitate transactions and enhance customer responses such as purchase intention and website loyalty. However, there has been little research on the external cues of website and psychological variables of consumer that could have positive influences on customer response. The purpose of this study is to investigate the influence of e-store personality on e-store loyalty through mediating variables such as e-store identification, e-store trust, and e-store engagement. The authors of this study develop the model and set up the six main hypotheses and a set of sub-hypotheses based on a literature review, shown in
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.
The increase of the supply of medical service and the increase of hospitals have intensified the competition of hospitals, and the advancement towards internationalization in the opening of medical industry has triggered the infinite competition of medical profession. In addition, the high expectation of customers and quality improvement in the medical care in accordance with the improvement of overall income, and the change of active role of medical consumers according to the popularization and the improvement of rights awareness reflect the customer needs and choice in the medical service. Customers wanted to receive the kind and pleasant service under the up-to-date medical service. Therefore, as a solution, hospital coordinators were emerged for the purpose of smooth treatment and customer satisfaction by generalizing all service of hospital. Accordingly, this thesis attempted to investigate the effect of hospital coordinator education curriculum on the education satisfaction and the quality of medical service. In order to solve the purpose of this study, I, author reviewed the existing literatures, established hypothesis, and verified hypothesis by using the variety of statistics techniques such as reliability, validity, frequency analysis, and regression analysis. The verification of hypothesis is as followings: First, among education training factors of hospital coordinators, the quality of instructor significantly affects the satisfaction of hospital coordinator education training. Second, among training factors of hospital coordinator, the attitude of trainee significantly affects the training satisfaction of hospital coordinator. Third, among education training factors of hospital coordinator, education course significantly affects the training satisfaction of hospital coordinator education. As the qualities of instructor are better equipped, the satisfaction of education becomes higher. It indicates that the education method of instructors is important as an index to represent the qualities of instructor such as the appropriateness of education method, preparation, passion, visual materials, the adequacy of education procession, and specialized knowledge, and it has important effect on the satisfaction of education. In order to enhance the satisfaction of hospital coordinator education, the creation of education environment, making trainee concentrate on the education, is required by appropriately allocating programs, arousing interest in education, based on the attitude of trainee, discussion, and preliminary programs, preparation, ahead of enforcement of education. Fourth, the satisfaction of hospital coordinator education training significantly affects the reliability among the qualities of medical service. Fifth, satisfaction of hospital coordinator education training significantly affects hospitality I kindness among the qualities of medical service. If the education satisfaction of trainee is high, it is effective in the practical application such as dealing with complaints, the duty performance for the patients, and so on in offering the medical service, related to reliability and furthermore, we can find the positive change in the attitude change of medical professions related to the reliability of hospital coordinator. In addition, in the process of offering medical services such as the kind explanation on the duty, rapid response to the customers inquiry, and tidy uniform, practical effect was verified. Sixth, the education training factor of hospital coordinator significantly affects the reliability among the quality of medical service. Seventh, the education training factors of hospital coordinator significantly affect hospitality/kindness. In the education of hospital coordinator, the methods to attract the interest of trainee by emphasizing reliability should be sought and for gaining the practical effect of hospital coordinator education, the sufficient preparation and investigation on the education curriculum should be prerequisite and under this condition, intensified discussion on the instructor and education course is needed. In the design of education course, more education hours and subjects should be allocated in the part of hospitality in order to improve the practical application of hospitality. Therefore, it is meaningful in a sense that this study newly approached the components of hospital coordinator education and the need to modify the quality components of medical service in accordance with the study subjects was raised. This study also finds its meaning in that it provides basic materials for the study of future hospital coordinator education by suggesting the system development model of hospital coordinator education through preliminary study of education training. In addition, this study is meaningful in the aspect that it suggested the direction of education training by showing how the hospital coordinator education training would applied to the hospital coordinator course of the Continuing Education Center at Pusan and Kyungnam National University to some extent. Since all investigation of this study was approached from the side of hospital coordinator, the thoughts of patients who are beneficiaries of medical service, and care givers cannot be identified. Therefore, the satisfaction of patients and care givers through the experience of medical service, which is the essential prerequisite of medical service, should be importantly considered and investigated. Accordingly, The study of comparing and analyzing the views of both patients and care givers should be carried out in the future.
The purposes of this study were to identify the consumer behavior using in campus specialty coffee shop and to establish the marketing strategies through Importance-Performance Analysis (IPA) of service quality. Questionnaires were distributed to 725 students at K University located in Masan, from April 23 to May 3, 2007. Finally, 621 questionnaires were included in the final analysis (response rate: 85.7%). For statistical analysis, SPSS (12.0) was used to conduct the descriptive analysis, t-test, factor analysis and reliability test. The results of this study were as follows. The average cost of using specialty coffee shop in campus was \ 2,096, the average staying time was 25.92 min and the average number of visits per month was 2.17 times. The importance level of 'employee's attitude', 'physical environment', 'sensory quality of coffee', 'beverage features', 'representativeness' were 3.88, 3.79, 3.73, 3.67, 3.28 points, respectively. Also, the performance level of 'sensory quality of coffee', 'beverage features', 'employee's attitude', 'physical environment', 'representativeness' were 3.13, 3.06, 3.05, 2.77, 2.61, respectively. The importance and performance levels of service quality of specialty coffee shop in campus were significantly different (p<.001). Establishment of marketing strategies for in campus speciality coffee shop was possible through the IPA of service quality. Strategies for improving customer satisfaction were to secure enough chairs/ tables, to procure comfortable chairs for customer and to ensure the quality of coffee bean and service of employee.
The impact of TV Drama success on TV Rating and the channel promotion effectiveness is very high. The cultural and business impact has been also demonstrated through the Korean Wave. Therefore, the early prediction of the blockbuster success of TV Drama is very important from the strategic perspective of the media industry. Previous studies have tried to predict the audience ratings and success of drama based on various methods. However, most of the studies have made simple predictions using intuitive methods such as the main actor and time zone. These studies have limitations in predicting. In this study, we propose a model for predicting the popularity of drama by analyzing the customer's viewing pattern based on various theories. This is not only a theoretical contribution but also has a contribution from the practical point of view that can be used in actual broadcasting companies. In this study, we collected data of 280 TV mini-series dramas, broadcasted over the terrestrial channels for 10 years from 2003 to 2012. From the data, we selected the most highly ranked and the least highly ranked 45 TV drama and analyzed the viewing patterns of them by 11-step. The various assumptions and conditions for modeling are based on existing studies, or by the opinions of actual broadcasters and by data mining techniques. Then, we developed a prediction model by measuring the viewing-time distance (difference) using Euclidean and Correlation method, which is termed in our study similarity (the sum of distance). Through the similarity measure, we predicted the success of dramas from the viewer's initial viewing-time pattern distribution using 1~5 episodes. In order to confirm that the model is shaken according to the measurement method, various distance measurement methods were applied and the model was checked for its dryness. And when the model was established, we could make a more predictive model using a grid search. Furthermore, we classified the viewers who had watched TV drama more than 70% of the total airtime as the "passionate viewer" when a new drama is broadcasted. Then we compared the drama's passionate viewer percentage the most highly ranked and the least highly ranked dramas. So that we can determine the possibility of blockbuster TV mini-series. We find that the initial viewing-time pattern is the key factor for the prediction of blockbuster dramas. From our model, block-buster dramas were correctly classified with the 75.47% accuracy with the initial viewing-time pattern analysis. This paper shows high prediction rate while suggesting audience rating method different from existing ones. Currently, broadcasters rely heavily on some famous actors called so-called star systems, so they are in more severe competition than ever due to rising production costs of broadcasting programs, long-term recession, aggressive investment in comprehensive programming channels and large corporations. Everyone is in a financially difficult situation. The basic revenue model of these broadcasters is advertising, and the execution of advertising is based on audience rating as a basic index. In the drama, there is uncertainty in the drama market that it is difficult to forecast the demand due to the nature of the commodity, while the drama market has a high financial contribution in the success of various contents of the broadcasting company. Therefore, to minimize the risk of failure. Thus, by analyzing the distribution of the first-time viewing time, it can be a practical help to establish a response strategy (organization/ marketing/story change, etc.) of the related company. Also, in this paper, we found that the behavior of the audience is crucial to the success of the program. In this paper, we define TV viewing as a measure of how enthusiastically watching TV is watched. We can predict the success of the program successfully by calculating the loyalty of the customer with the hot blood. This way of calculating loyalty can also be used to calculate loyalty to various platforms. It can also be used for marketing programs such as highlights, script previews, making movies, characters, games, and other marketing projects.
In this work, satellite FE (finite element) model updating for the prediction of the effect of micro-vibration is described. In the case of satellites launched in low earth orbit, high agility and more mission accomplishments are required by the customer in order to procure many images from satellites. To achieve the goal, many mechanisms, including high capacity wheels and antennas with multi-axis gimbals have been widely adopted, but they become a source of micro-vibration which could significantly deteriorate the quality of images. To investigate the effect due to the micro-vibration in orbit on the ground, a prediction is conducted through an integrated model coupling the measured jitter sources with FE (finite element) model. Before prediction, the FE model is updated to match simulation results with the modal survey test. Subsequently, the quality of FE model is evaluated in terms of frequency deviation error, the resemblance of mode shapes and FRFs (frequency response functions) between test and analysis.
In response to the changing demands of ever competitive market, SK Telecom has built a new marketing system that can support dynamic marketing campaigns and, at the same time, scale up to the large volumes of data and transactions for the next decade. The system which employs Unix-based client-server (using Web browser interfaces) architecture will replace the current mainframe-based COIS system. The project, named NGM (Next Generation Marketing ), is unprecedentedly large in scale. However, both managerial and technical problems led the project into a crisis. The application framework that depended on a software solution from a major global vendor could not support the dynamic functionalities required for the new system. In March 2005, SK telecom declared the suspension of the NGM project. The second phase of the project started in May 2005 following a comprehensive replanning. It was decided that no single existing solution could cope with the complexity of the new system and hence the new system would be custom-built. As such. a number of technical challenges emerged. In this paper, we report on the three key dimensions of technical challenges - middleware and application framework, database architecture and tuning, and system performance. The processes and approaches, adopted in building NGM system, may be viewed as "best practices" in the telecom industry. The completed NGM system, now called "U.key System," successfully came into operation on the ninth of October, 2006. This new infrastructure is expected to give birth to a series of innovative, fruitful, and customer-oriented applications in the near future.
There is a big attention to digital convergence products(DCP) nowadays. However, consumers' response on the DCP is not always positive. These products may not match consumers' value and consumers may not know how to use them, because the DCP is generally innovative products. DCP marketers should learn that why consumers do not purchase them. Thus, this paper examines and identifies the consumers' purchase-avoiding psychological factors and antecedents on DCP. In detail, It is empirically checked that how the relationship between purchase-preventing factors such as complexity, incongruence, uncertainty, and unreasonability and purchase-avoiding psychological factors such as dissonance, innovation resistence, and perceived loss is. Also, these purchase-avoiding psychological factors' influence on the purchase-intention is empirically checked. As results, complexity and incongruence have an effect on the innovation resistence significantly. Uncertainty and unreasonability influence perceived loss variable. Unreasonability also influences consumers' cognitive dissonance variable. Additionally, cognitive dissonance have an influence on innovation resistence positively, and such innovation resistence influence consumer's purchase-intention negatively. Therefore, marketers should think twice about the roles of these purchase-preventing factors before launching.
The purpose of this study was to analyze the effect of the consumer-brand relationship quality on the brand loyalty in family restaurants. Questionnaires were distributed to 320 students in K University located in Masan, who were sampled by convenience-sampling method. The surveys were conducted from November, 10 to 24, 2005. Of the 287 returned questionnaires, 15 unusable questionnaires were excluded to leave 272 for use in the final analysis(response rate: 85.0%). For the statistical analysis, SPSS(12.0)was used to conduct the descriptive analysis, factor analysis, reliability analysis, correlation and multiple regression analysis. The results of this study showed that 2 constructs (satisfaction and intimacy) of consumer-brand relationship quality have significantly positive effects on the brand loyalty in family restaurants(p<.01). This indicates that as consumer-brand relationship quality strengthens, the customer's brand loyalty increases. In conclusion, food service managers in family restaurants should focus on the marketing strategies to strengthen the quality of consumer-brand relationship in order to increase the brand loyalty of customers.
. This model is composed of four paths such as dimensions of e-store personality. First of all, hypothesis 1 is partially supported because sub-hypothesis 1-1 and 1-2 are supported, whereas sub-hypothesis 1-3, 1-4, and 1-5 are rejected. Specifically, it reveals that warmth and sophistication dimensions in e-store personality have positive influence on e-store identification, however, activity, progressiveness, and strictness does not have any significant relationship on e-store identification. Secondly, hypothesis 2 was supported. Therefore, it can be said that e-store identification has a positive impact on e-store trust. Thirdly, hypothesis 3 is also supported. Hence, there is a positive relationship between e-store identification and e-store engagement. Fourthly, hypothesis 4 is supported too. e-store identification has a positive influence on e-store loyalty. Fifthly, hypothesis 5 is also accepted. This indicates that e-store trust is a precedent variable which positively affects e-store loyalty. Lastly, it reveals that e-store engagement has a positive impact on e-store loyalty. Therefore, hypothesis 6 is supported. The findings of the study imply that some dimensions of e-store personality have a positive influence on e-store identification, and that e-store identification has direct and indirect influence on e-store loyalty through e-store trust and e-store engagement positively. These results also suggest that the e-store identification in e-store personality is a precedent variable which positively affects e-store loyalty directly and indirectly through e-store trust and engagement as a mediating variable. Therefore, e-store marketers need to implement website strategy based on e-store personality, e-store identification, e-store trust, and e-store engagement to meet customers' psychological needs and enhance e-store loyalty. Finally, the limitations and future study directions based on this study are discussed.
Analysis of Success Cases of InsurTech and Digital Insurance Platform Based on Artificial Intelligence Technologies: Focused on Ping An Insurance Group Ltd. in China
(인공지능 기술 기반 인슈어테크와 디지털보험플랫폼 성공사례 분석: 중국 평안보험그룹을 중심으로)
The Effect of Hospital Service Coordinator Education Curriculum on the Education Satisfaction and the Quality of Medical Service
(병원서비스코디네이터 교육과정이 교육만족과 의료서비스 품질에 미치는 영향)
Importance-Performance Analysis of Service Quality of In Campus Specialty Coffee Shop
(대학내 커피전문점 서비스품질에 대한 중요도-수행도 분석)
Prediction of a hit drama with a pattern analysis on early viewing ratings
(초기 시청시간 패턴 분석을 통한 대흥행 드라마 예측)
Satellite finite element model updating for the prediction of the effect of micro-vibration
(미소진동 영향성 예측을 위한 인공위성 유한요소모델 보정)
A Case Study on SK Telecom's Next Generation Marketing System Development
(SK텔레콤의 차세대 마케팅 시스템 개발사례 연구)
Purchasing Avoidance of Digital Convergence Products: Focusing on the Customer's Psychological Factors and the Innovation Resistance
(디지털 컨버전스제품 구매회피에 관한 연구: 소비자의 심리적 요인과 혁신저항을 중심으로)
Effect of Consumer-Brand Relationship Quality on Brand Loyalty in Family Restaurants
(패밀리 레스토랑의 소비자-브랜드 관계의 질이 브랜드 충성도에 미치는 영향 : 마산지역 대학생을 대상으로)
이메일무단수집거부
이용약관
제 1 장 총칙
제 2 장 이용계약의 체결
제 3 장 계약 당사자의 의무
제 4 장 서비스의 이용
제 5 장 계약 해지 및 이용 제한
제 6 장 손해배상 및 기타사항
Detail Search
Image Search
(β)