• Journal of Intelligence and Information Systems
• /
• 제18권4호
• /
• pp.43-57
• /
• 2012

To enhance the competitive advantage in a constantly changing business environment, an enterprise management must make the right decision in many business activities based on both internal and external information. Thus, providing accurate information plays a prominent role in management's decision making. Intuitively, historical data can provide a feasible estimate through the forecasting models. Therefore, if the service department can estimate the service quantity for the next period, the service department can then effectively control the inventory of service related resources such as human, parts, and other facilities. In addition, the production department can make load map for improving its product quality. Therefore, obtaining an accurate service forecast most likely appears to be critical to manufacturing companies. Numerous investigations addressing this problem have generally employed statistical methods, such as regression or autoregressive and moving average simulation. However, these methods are only efficient for data with are seasonal or cyclical. If the data are influenced by the special characteristics of product, they are not feasible. In our research, we propose a forecasting framework that predicts service demand of manufacturing organization by combining Case-based reasoning (CBR) and leveraging an unsupervised artificial neural network based clustering analysis (i.e., Self-Organizing Maps; SOM). We believe that this is one of the first attempts at applying unsupervised artificial neural network-based machine-learning techniques in the service forecasting domain. Our proposed approach has several appealing features : (1) We applied CBR and SOM in a new forecasting domain such as service demand forecasting. (2) We proposed our combined approach between CBR and SOM in order to overcome limitations of traditional statistical forecasting methods and We have developed a service forecasting tool based on the proposed approach using an unsupervised artificial neural network and Case-based reasoning. In this research, we conducted an empirical study on a real digital TV manufacturer (i.e., Company A). In addition, we have empirically evaluated the proposed approach and tool using real sales and service related data from digital TV manufacturer. In our empirical experiments, we intend to explore the performance of our proposed service forecasting framework when compared to the performances predicted by other two service forecasting methods; one is traditional CBR based forecasting model and the other is the existing service forecasting model used by Company A. We ran each service forecasting 144 times; each time, input data were randomly sampled for each service forecasting framework. To evaluate accuracy of forecasting results, we used Mean Absolute Percentage Error (MAPE) as primary performance measure in our experiments. We conducted one-way ANOVA test with the 144 measurements of MAPE for three different service forecasting approaches. For example, the F-ratio of MAPE for three different service forecasting approaches is 67.25 and the p-value is 0.000. This means that the difference between the MAPE of the three different service forecasting approaches is significant at the level of 0.000. Since there is a significant difference among the different service forecasting approaches, we conducted Tukey's HSD post hoc test to determine exactly which means of MAPE are significantly different from which other ones. In terms of MAPE, Tukey's HSD post hoc test grouped the three different service forecasting approaches into three different subsets in the following order: our proposed approach > traditional CBR-based service forecasting approach > the existing forecasting approach used by Company A. Consequently, our empirical experiments show that our proposed approach outperformed the traditional CBR based forecasting model and the existing service forecasting model used by Company A. The rest of this paper is organized as follows. Section 2 provides some research background information such as summary of CBR and SOM. Section 3 presents a hybrid service forecasting framework based on Case-based Reasoning and Self-Organizing Maps, while the empirical evaluation results are summarized in Section 4. Conclusion and future research directions are finally discussed in Section 5.

• Journal of Intelligence and Information Systems
• /
• 제24권2호
• /
• pp.1-19
• /
• 2018

Since stock movements forecasting is an important issue both academically and practically, studies related to stock price prediction have been actively conducted. The stock price forecasting research is classified into structured data and unstructured data, and it is divided into technical analysis, fundamental analysis and media effect analysis in detail. In the big data era, research on stock price prediction combining big data is actively underway. Based on a large number of data, stock prediction research mainly focuses on machine learning techniques. Especially, research methods that combine the effects of media are attracting attention recently, among which researches that analyze online news and utilize online news to forecast stock prices are becoming main. Previous studies predicting stock prices through online news are mostly sentiment analysis of news, making different corpus for each company, and making a dictionary that predicts stock prices by recording responses according to the past stock price. Therefore, existing studies have examined the impact of online news on individual companies. For example, stock movements of Samsung Electronics are predicted with only online news of Samsung Electronics. In addition, a method of considering influences among highly relevant companies has also been studied recently. For example, stock movements of Samsung Electronics are predicted with news of Samsung Electronics and a highly related company like LG Electronics.These previous studies examine the effects of news of industrial sector with homogeneity on the individual company. In the previous studies, homogeneous industries are classified according to the Global Industrial Classification Standard. In other words, the existing studies were analyzed under the assumption that industries divided into Global Industrial Classification Standard have homogeneity. However, existing studies have limitations in that they do not take into account influential companies with high relevance or reflect the existence of heterogeneity within the same Global Industrial Classification Standard sectors. As a result of our examining the various sectors, it can be seen that there are sectors that show the industrial sectors are not a homogeneous group. To overcome these limitations of existing studies that do not reflect heterogeneity, our study suggests a methodology that reflects the heterogeneous effects of the industrial sector that affect the stock price by applying k-means clustering. Multiple Kernel Learning is mainly used to integrate data with various characteristics. Multiple Kernel Learning has several kernels, each of which receives and predicts different data. To incorporate effects of target firm and its relevant firms simultaneously, we used Multiple Kernel Learning. Each kernel was assigned to predict stock prices with variables of financial news of the industrial group divided by the target firm, K-means cluster analysis. In order to prove that the suggested methodology is appropriate, experiments were conducted through three years of online news and stock prices. The results of this study are as follows. (1) We confirmed that the information of the industrial sectors related to target company also contains meaningful information to predict stock movements of target company and confirmed that machine learning algorithm has better predictive power when considering the news of the relevant companies and target company's news together. (2) It is important to predict stock movements with varying number of clusters according to the level of homogeneity in the industrial sector. In other words, when stock prices are homogeneous in industrial sectors, it is important to use relational effect at the level of industry group without analyzing clusters or to use it in small number of clusters. When the stock price is heterogeneous in industry group, it is important to cluster them into groups. This study has a contribution that we testified firms classified as Global Industrial Classification Standard have heterogeneity and suggested it is necessary to define the relevance through machine learning and statistical analysis methodology rather than simply defining it in the Global Industrial Classification Standard. It has also contribution that we proved the efficiency of the prediction model reflecting heterogeneity.

• The Journal of Korean Medical History
• /
• 제18권2호
• /
• pp.197-227
• /
• 2005

Heojun was the top scientist on Medicine in the 16th and 17th centuries and wrote the Dongeubogam describing the top-level medical theory and technology. So far, his outlook on nature has been disregarded even though his medicine is still effective. Through this study, I would like to know if his outlook on nature as well as his medicine is still effective. The conclusions are as follows: 1. According to his output, the origin of the universe started from the spinning of One Gi(一氣) which is quite different from Hawking's theory. Hawking assumed that the origin of the universe started from the Big-bang and will end to the Big-crunch. However, the current report on the origin of a star is quite similar to Heojun's theory and we acknowledge that his view on the origin of the universe is still effective. 2. According to his output, the universe repeats expanding and contracting forever while Hawking assumed it will come to the end, the Big-crunch, based on the expanding universe theory. Some scientists assists that Hawking's assumption should have some contradictions. Now, we acknowledge that Heojun's universal cycling theory which corresponds with modern physical theories is still effective, which would lead to a new environmental movement. 3. His view on the structure of the universe is quite different from the output of the current science, which results from his thought that the nature should be reviewed from the point of human's view. His view on the structure will be able to be updated based on the output of the current science. 4. The universe analogy started from the East Asian area as well as the Greek and Roman area in the ancient. The idea has disappeared since the scientific revolution era in the West while the idea has been deepened and abundant in the East and has become one of the major philosophical bases. Heojun emphasized its importance from the beginning of his book. 5. The nation analogy has been popular all times and places. According to his output, governing a country is like controlling one's body. 6. According to Needham's output, the universe analogy and the nation analogy were based on the ancient developed alchemy. And Harper assumed that Taiosm was based on the macrobiotic hygiene which was developed by the ancient developed alchemists. We acknowledge that xian(仙) cult, macrobiotic hygiene, medicine, alchemy and the ancient philosophy started from our ancients. Heojun's output restored our ancient tradition by combining the macrobiotic hygiene and philosophy with medicine. 7. Roughly predicting yearly weather would be unacceptable by the current scientist but Heojun's yearly weather forecast is still used in the clinic and seems effective to prepare from any epidemic disease. 8. 'Day and Night' and Four seasons are the most important factors to the macrobiotic hygiene according to the Dongeubogam. The new environmental movements should be based on the most important factors, otherwise the human beings as well as the environment would fail to survive. 9. Wind, Coldness, Heat, Humidity, Dryness and Fire represents weather. The six weather factors represent one of six phases of a year which is decided by the areal factors. Heojun preferred the six factors generated in the body itself to them from the outside. He thought a human being was a universe and the six factors generated in the body responded to the factors of the outside. 10. According to his output, Heat and Humidity are the most important factors which make a human being ill. 11. Life span, disease, food, and dwelling are dependent upon the geographical feature, according to Heojun's output. In addition, one's appearance and his five viscera and the six entrails depend on the food as well as the geographical feature. 12. Heath is related with the environment and they effects upon each other. If one is weak, he will be deeply effected by the nature. On the other hand, if one is strong, he will effect on the nature. That's why people live together. 13. According to Heojun's work, the society is an important factor comprising the environment. During a peaceful era, the society becomes stable and human beings are stable as well while they will be on fire during a chaotic era. 14. Medicine deals with human beings who live in the nature, so any medical book cannot be excellent unless it has any description on the nature. Heojun's outlook on the nature turned out to be logical and suitable even from the point of the current view and it is still effective as if his clinical knowledge and technology are still effective. Something unsuitable may be substituted with the output of the current science.

• Journal of Intelligence and Information Systems
• /
• 제22권4호
• /
• pp.177-192
• /
• 2016

Machine learning is a field of artificial intelligence. It refers to an area of computer science related to providing machines the ability to perform their own data analysis, decision making and forecasting. For example, one of the representative machine learning models is artificial neural network, which is a statistical learning algorithm inspired by the neural network structure of biology. In addition, there are other machine learning models such as decision tree model, naive bayes model and SVM(support vector machine) model. Among the machine learning models, we use SVM model in this study because it is mainly used for classification and regression analysis that fits well to our study. The core principle of SVM is to find a reasonable hyperplane that distinguishes different group in the data space. Given information about the data in any two groups, the SVM model judges to which group the new data belongs based on the hyperplane obtained from the given data set. Thus, the more the amount of meaningful data, the better the machine learning ability. In recent years, many financial experts have focused on machine learning, seeing the possibility of combining with machine learning and the financial field where vast amounts of financial data exist. Machine learning techniques have been proved to be powerful in describing the non-stationary and chaotic stock price dynamics. A lot of researches have been successfully conducted on forecasting of stock prices using machine learning algorithms. Recently, financial companies have begun to provide Robo-Advisor service, a compound word of Robot and Advisor, which can perform various financial tasks through advanced algorithms using rapidly changing huge amount of data. Robo-Adviser's main task is to advise the investors about the investor's personal investment propensity and to provide the service to manage the portfolio automatically. In this study, we propose a method of forecasting the Korean volatility index, VKOSPI, using the SVM model, which is one of the machine learning methods, and applying it to real option trading to increase the trading performance. VKOSPI is a measure of the future volatility of the KOSPI 200 index based on KOSPI 200 index option prices. VKOSPI is similar to the VIX index, which is based on S&P 500 option price in the United States. The Korea Exchange(KRX) calculates and announce the real-time VKOSPI index. VKOSPI is the same as the usual volatility and affects the option prices. The direction of VKOSPI and option prices show positive relation regardless of the option type (call and put options with various striking prices). If the volatility increases, all of the call and put option premium increases because the probability of the option's exercise possibility increases. The investor can know the rising value of the option price with respect to the volatility rising value in real time through Vega, a Black-Scholes's measurement index of an option's sensitivity to changes in the volatility. Therefore, accurate forecasting of VKOSPI movements is one of the important factors that can generate profit in option trading. In this study, we verified through real option data that the accurate forecast of VKOSPI is able to make a big profit in real option trading. To the best of our knowledge, there have been no studies on the idea of predicting the direction of VKOSPI based on machine learning and introducing the idea of applying it to actual option trading. In this study predicted daily VKOSPI changes through SVM model and then made intraday option strangle position, which gives profit as option prices reduce, only when VKOSPI is expected to decline during daytime. We analyzed the results and tested whether it is applicable to real option trading based on SVM's prediction. The results showed the prediction accuracy of VKOSPI was 57.83% on average, and the number of position entry times was 43.2 times, which is less than half of the benchmark (100 times). A small number of trading is an indicator of trading efficiency. In addition, the experiment proved that the trading performance was significantly higher than the benchmark.

• Journal of Preventive Medicine and Public Health
• /
• 제16권1호
• /
• pp.135-152
• /
• 1983

Emergency medical service is an important part of the health care delivery system, and the optimal allocation of resources and their efficient utilization are essentially demanded. Since these conditions are the prerequisite to prompt treatment which, in turn, will be crucial for life saving and in reducing the undesirable sequelae of the event. This study, taking the hyperbaric chamber for carbon monoxide poisoning as an example, is to develop a stochastic approach for solving the problems of optimal allocation of such emergency medical facility in Korea. The hyperbaric chamber, in Korea, is used almost exclusively for the treatment of acute carbon monoxide poisoning, most of which occur at home, since the coal briquette is used as domestic fuel by 69.6 per cent of the Korean population. The annual incidence rate of the comatous and fatal carbon monoxide poisoning is estimated at 45.5 per 10,000 of coal briquette-using population. It offers a serious public health problem and occupies a large portion of the emergency outpatients, especially in the winter season. The requirement of hyperbaric chambers can be calculated by setting the level of the annual queueing rate, which is here defined as the proportion of the annual number of the queued patients among the annual number of the total patients. The rate is determined by the size of the coal briquette-using population which generate a certain number of carbon monoxide poisoning patients in terms of the annual incidence rate, and the number of hyperbaric chambers per hospital to which the patients are sent, assuming that there is no referral of the patients among hospitals. The queueing occurs due to the conflicting events of the 'arrival' of the patients and the 'service' of the hyperbaric chambers. Here, we can assume that the length of the service time of hyperbaric chambers is fixed at sixty minutes, and the service discipline is based on 'first come, first served'. The arrival pattern of the carbon monoxide poisoning is relatively unique, because it usually occurs while the people are in bed. Diurnal variation of the carbon monoxide poisoning can hardly be formulated mathematically, so empirical cumulative distribution of the probability of the hourly arrival of the patients was used for Monte Carlo simulation to calculate the probability of queueing by the number of the patients per day, for the cases of one, two or three hyperbaric chambers assumed to be available per hospital. Incidence of the carbon monoxide poisoning also has strong seasonal variation, because of the four distinctive seasons in Korea. So the number of the patients per day could not be assumed to be distributed according to the Poisson distribution. Testing the fitness of various distributions of rare event, it turned out to be that the daily distribution of the carbon monoxide poisoning fits well to the Polya-Eggenberger distribution. With this model, we could forecast the number of the poisonings per day by the size of the coal-briquette using population. By combining the probability of queueing by the number of patients per day, and the probability of the number of patients per day in a year, we can estimate the number of the queued patients and the number of the patients in a year by the number of hyperbaric chamber per hospital and by the size of coal briquette-using population. Setting 5 per cent as the annual queueing rate, the required number of hyperbaric chambers was calculated for each province and for the whole country, in the cases of 25, 50, 75 and 100 per cent of the treatment rate which stand for the rate of the patients treated by hyperbaric chamber among the patients who are to be treated. Findings of the study were as follows. 1. Probability of the number of patients per day follows Polya-Eggenberger distribution. $$P(X=\gamma)=\frac{\Pi\limits_{k=1}^\gamma[m+(K-1)\times10.86]}{\gamma!}\times11.86^{-{(\frac{m}{10.86}+\gamma)}}$$ when$${\gamma}=1,2,...,n$$$$P(X=0)=11.86^{-(m/10.86)}$$ when $${\gamma}=0$$ Hourly arrival pattern of the patients turned out to be bimodal, the large peak was observed in $7 : 00{\sim}8 : 00$ a.m., and the small peak in $11 : 00{\sim}12 : 00$ p.m. 2. In the cases of only one or two hyperbaric chambers installed per hospital, the annual queueing rate will be at the level of more than 5 per cent. Only in case of three chambers, however, the rate will reach 5 per cent when the average number of the patients per day is 0.481. 3. According to the results above, a hospital equipped with three hyperbaric chambers will be able to serve 166,485, 83,242, 55,495 and 41,620 of population, when the treatmet rate are 25, 50, 75 and 100 per cent. 4. The required number of hyperbaric chambers are estimated at 483, 963, 1,441 and 1,923 when the treatment rate are taken as 25, 50, 75 and 100 per cent. Therefore, the shortage are respectively turned out to be 312, 791. 1,270 and 1,752. The author believes that the methodology developed in this study will also be applicable to the problems of resource allocation for the other kinds of the emergency medical facilities.