• 한국콘텐츠학회논문지
• /
• 제7권7호
• /
• pp.161-170
• /
• 2007

국 내외적으로 e-비즈니스는 일반적인 상거래 유형으로 자리 잡고 있다. 최초 e-비즈니스는 전자상거래라는 용어로 시작되었다. 그러나 점점 단순한 전자상거래보다 포괄적인 전자상거래 방식으로 변화되었다. 이러한 시점에서 한국의 e-비즈니스 시장에 대한 연구를 통해 성숙된 e-비즈니스 시장의 진입과 세계시장을 이끌 수 있는 토대를 마련하고자 한다. 이를 위해 한국 시장의 e-비즈시장 활성화를 위한 핵심성공요인의 성숙 단계를 측정하였다. 시간의 흐름에 따라 변화되는 핵심성공요인 의 중요도를 측정하여 한국 시장에서의 e-비즈니스의 활성화의 수준을 분석하였다. 이를 통해, 향후 e-비즈니스 시장의 발전 방향을 예측하고, 이에 대응할 수 있는 방안을 제공하고자 한다.

• Fisheries and Aquatic Sciences
• /
• 제15권4호
• /
• pp.345-352
• /
• 2012

To predict catches of Pacific anchovy Engraulis japonicus larvae, anchovy eggs were collected in the coastal waters off Gunsan, Korea, in the Yellow Sea during the main spawning season (June to July) from 2003 to 2009. A ring net was repeatedly towed vertically at 10 stations during the daytime to sample eggs. Catch data estimated by auction sales were obtained from the Fisheries Cooperatives Union of Gunsan City and daily water temperature data in the outer harbor of Gunsan City during the survey periods were obtained from the National Oceanographic Research Institute. A significant relationship was found between anchovy egg density from June to July and larval catch from July to October in the same year. Catch of anchovy larvae in Gunsan were also high when optimal growth temperatures were recorded in the coastal waters off Gunsan in July. Although the recruitment success or failure of anchovy larvae can be predicted from variability in egg density, we suggest that mean daily water temperature is a more efficient indicator for predicting variability in catches of larval anchovy in the Yellow Sea.

• 한국건설관리학회논문집
• /
• 제7권2호
• /
• pp.162-170
• /
• 2006

부동산분야에서 전통적인 예측방법과 비교하여 보다 예측력을 높일 수 있는 방법을 찾으려 한다. 이에 앞서 신경망 모형의 적용가능성을 살펴보고, 기존의 연구를 토대로 한 신경망 이론의 정의, 구조, 장단점 등을 살펴본다. 구체적인 적용가능성을 확인하기 위하여 동일 데이터로 회귀분석과 신경망분석을 통한 모형을 구축하고, 예측정확도 측면에서 신경망모형의 적용 가능성을 검토한다. 부동산학에서 기존에 회귀분석에 치우쳐 있던 연구방법을 신경망분석까지 확장하고, 특히 예측정확도 측면에서 우수성이 검증되고 있는 신경망모형에 대한 연구를 활성화 하고자 하는데 본 연구의 목적이 있다. 연구방법으로는 분양가격에 영향을 주는 거시경제변수를 모형화 한다. 그 모형설정 후 회귀분석과 신경망분석으로 결과를 비교하여 보다 예측 정확도가 높은 것을 찾는다. 그 결과 신경망모형의 예측정확도가 상당히 높게 나타났다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제27권3호
• /
• pp.123-140
• /
• 2018

Purpose The purpose of this study is to explore the optimal trading frequency which is useful for stock price prediction by using deep learning for charting image data. We also want to identify the appropriate time for accurate forecasting of stock price when performing pattern analysis. Design/methodology/approach In order to find the optimal trading frequency patterns and forecast timings, this study is performed as follows. First, stock price data is collected using OpenAPI provided by Daishin Securities, and candle chart images are created by data frequency and forecasting time. Second, the patterns are generated by the charting images and the learning is performed using the CNN. Finally, we find the optimal trading frequency patterns and forecasting timings. Findings According to the experiment results, this study confirmed that when the 10 minute frequency data is judged to be a decline pattern at previous 1 tick, the accuracy of predicting the market frequency pattern at which the market decreasing is 76%, which is determined by the optimal frequency pattern. In addition, we confirmed that forecasting of the sales frequency pattern at previous 1 tick shows higher accuracy than previous 2 tick and 3 tick.

• Asia pacific journal of information systems
• /
• 제16권4호
• /
• pp.239-254
• /
• 2006

Location-based advertising or application has been one of the drivers of third-generation mobile operators' marketing efforts in the past few years. As a result, many studies on location-based marketing or advertising have been proposed for recent several years. However, these approaches have two common shortcomings. First. most of them just suggested the theoretical architectures, which were too abstract to apply it to the real-world cases. Second, many of these approaches only consider service provider (seller) rather than customers (buyers). Thus, the prior approaches fit to the automated sales or advertising rather than the implementation of CRM. To mitigate these limitations, this study presents a novel advertisement recommendation model for mobile users. We call our model MAR-CF (Mobile Advertisement Recommender using Collaborative Filtering). Our proposed model is based on traditional CF algorithm, but we adopt the multi-dimensional personalization model to conventional CF for enabling location-based advertising for mobile users. Thus, MAR-CF is designed to make recommendation results for mobile users by considering location, time, and needs type. To validate the usefulness of our recommendation model. we collect the real-world data for mobile advertisements, and perform an empirical validation. Experimental results show that MAR-CF generates more accurate prediction results than other comparative models.

• The International Journal of Costume Culture
• /
• 제4권1호
• /
• pp.44-60
• /
• 2001

The purpose of this study is to present suggestions to improve the problems the domestic department stores face by analyzing and comparing the status of the development of PB which is absolutely critical for the specialized domestic department stores to survive, and to search for the future course which may lead to boosting sales and profit by developing the strategic PB products. Selected for this study were atotal of 20 PB's out of domestic as well s foreign PB's in the 4 big department stores. The data were analyzed with SAS package employed as per the by items frequency, percent, mean and standard deviation. From the above study, following viewpoints can be taken into account for the future development of PB ; First, the active will of the excutive is basically necessary for successful development of PB, by relying on long-term investment. Second, the existing mid or low-price goods should be in line with the mid or high price one's development for domestic merchandising with focus on middle or high class society. Third, the stock burden, biggest problem of PB, can be solved by discount policy at optimum prices and success rate of merchandising prediction.

• Industrial Engineering and Management Systems
• /
• 제15권4호
• /
• pp.324-334
• /
• 2016

Manufacturers and retailers are interested in how prices, promotions, discounts and other marketing variables can influence the sales and shares of the products that they produce or sell. Therefore, many models have been developed to predict the brand share. Since the customer choice models are usually used to predict the market share, here we use hybrid model of Probabilistic Neural Network and Artificial Bee colony Algorithm (PNN-ABC) that we have introduced to model consumer choice to predict brand share. The evaluation process is carried out using the same data set that we have used for modeling individual consumer choices in a retail coffee market. Then, to show good performance of this model we compare it with Artificial Neural Network with one hidden layer, Artificial Neural Network with two hidden layer, Artificial Neural Network trained with genetic algorithms (ANN-GA), and Probabilistic Neural Network. The evaluated results show that the offered model is outperforms better than other previous models, so it can be use as an effective tool for modeling consumer choice and predicting market share.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2014년도 추계학술발표대회
• /
• pp.890-893
• /
• 2014

IT산업의 새로운 패러다임으로 빅데이터 분석이 주요한 기술로 부각되고 있다. 본 논문에서는 빅데이터를 수집, 분석하여 이를 통해 피자 판매량을 예측하는 모델을 제안한다. 판매량 예측을 위하여 과거 판매 데이터와 함께 공휴일, 날씨, 뉴스기사, 경제지표, 트렌드, 스포츠 이벤트 등의 데이터를 수집하여 이용하였으며, 판매량 예측 방법으로는 회기분석과 인공신경망 학습 등을 사용하여 빅데이터를 사용하지 않은 경우와 정확도를 비교하였다. 실험 결과 빅데이터를 이용함으로써 예측 오차율이 5%이상 향상됨을 확인하였다.

• 유통과학연구
• /
• 제19권11호
• /
• pp.49-57
• /
• 2021

Purpose: In this study, we try to figure out the appropriate size of commercial districts in the original downtown area through empirical studies targeting the Jinju Central Commercial Area in Gyeongnam and Cheonan Station in Chungnam, which are trying to regenerate a specific space that has been lost through government projects. Research design, data and methodology: The current status and characteristics of the shopping district were examined through on-site surveys of the central business district of Jinju, Gyeongnam Province, and Cheonan Station, Chungnam Province, and the size of the empty stores was determined. In addition, the standard median income was used as the survey data along with the survey of the mobile population in the commercial area. Result: The analysis result shows that 883 stores should be maintained considering the overall expenditure and gross sales profit within Cheonan Station in South Chungcheong Province. Currently, considering spending and margins in the Commercial Area, Jinju Central Commercial Area is a place where 222 stores can be sold excessively, and a proper commercial supply plan is needed. Conclusions: In this study, we conducted a demand prediction study in the commercial sector of the most basic sector to regenerate the commercial sector through major regional commercial districts.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권5호
• /
• pp.667-678
• /
• 2021

The industrial life cycle theory was extended to the product life cycle theory and the corporate life cycle theory, but a conceptual life cycle was presented, and quantitative empirical evidence for this was insufficient. It is intended to improve appropriate resource planning and resource allocation by quantitatively predicting the industrial cycle and its position (age) in the cycle. Human resources, tangible assets, and industrial output analysis were conducted based on 28 years of actual data of 39 industries in Korea by applying the Gompertz model, which is a population ecology prediction model. By predicting with the Gompertz model, the coefficient of determination R2 value was 97% or more, confirming the high suitability with the actual cumulative sales value of the industry. A numerical model for calculating the life cycle of each industry, calculating the saturation of input resources for each industry, and diagnosing the financial stability of the industry was presented. These results will contribute to the decision-making of industrial policy officers for budget planning appropriately for each stage of industry development. Future research will apply the numerical model of this study to foreign national industries, complete an inter-industry convergence diagnostic model (e.g. ease of convergence, suitability of convergence, etc.) for renewal of fading industries.