• 서비스연구
• /
• 제12권4호
• /
• pp.82-93
• /
• 2022

외식서비스산업은 지속가능한 세계 식품 소비의 주요 원동력이다. 외식소비행동을 이해함으로써, 식당 관리자들은 수요를 예측하고 소비 전(前)단계에서 음식 낭비를 줄일 수 있다. 본 연구는 식당과 카페의 영향요인과 고객 수 간의 관계를 조사한다. 이러한 요인들은 비와 기온을 포함한 날씨와 관련된 요인들과 시험 기간과 요일을 포함한 학교 관련 요인들이다. 이 네 가지 요인에 기초하여 가능한 조합은 24개였다. 각 평일 조합에 대해서는 3가지 요일을 대표일로 정하였다. 각 주말 조합에 대해서는 1가지 요일을 대표일로 정하였다. 일 년 중 총 48일이 표본으로 추출되었다. 고객 자료는 한국의 한 대학 캠퍼스에 있는 6개의 식당과 카페에서 수집되었다. 고객 수에 대한 각 변수의 상대적 중요도를 결정하기 위해 컨조인트 분석(Conjoint Analysis)이 사용되었다. 이어 효용 값 (Utility Score)를 표준화하여 고객 수가 최고점에 도달했을 때 최적의 상태를 찾도록 매핑 (Mapping) 하였다. 또한 피어슨 상관 계수(Pearson's Correlation Coefficient)를 사용하여 각 점포의 매출을 비교하였다. 본 연구 결과는 온도와 비의 영향이 고객 수와 상관관계가 있다는 것을 뒷받침하였다. 또한, 고객 수를 예측하는 데 있어서 온도가 비보다 훨씬 더 중요하다는 것이 발견되었다. 본 논문은 식음료 수요를 예측하고 식사 선택을 예측하기 위해 날씨를 사용하는 것의 시사점에 대해 논의하였다.

• 대한인간공학회지
• /
• 제26권1호
• /
• pp.79-85
• /
• 2007

Demand forecasting methods for a consumer product such as TV or refrigerator are widely known. However, sales forecast for a brand new product cannot be estimated using conventional forecasting methods. This study proposes a five-step procedure in forecasting a newly developed product. Step one defines functions in a High Touch product in order to estimate relative attraction of the product to consumer group. In step two, for a comparison purpose, a compatible product that is successfully penetrated into market is selected. Step three breaks a target population into many segments based on demography. Step four calculates relative attraction between the High Touch product and the compatible product. Finally, market penetration rate of the High Touch product is estimated using a bell-shaped diffusion curve of the compatible product. The process offers a method to estimate potential demand and growth pattern of the new High Touch product.

• 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.

• 디자인학연구
• /
• 제14권1호
• /
• pp.93-101
• /
• 2001

This study suggested how to apply it decision-making of product development rapidly by design evaluation process to objectify and the result to quantify with viewpoint of design evaluation sets to marketability. Coverage of this method limited to the evaluation stage of design concept. The procedure of study, first of all, referred to some type of design evaluation method and their feature. And next, referred to some kinds of demand forecasting for marketing. Above an, this study focused on the method of demand forecasting by buying intentions surveys proper to the marketability evaluation of new product design. On a case study, I had investigated preference survey and buying intentions surveys about the design proposal of "language master audio". I selected the best design proposal through the conjoint analysis and also investigated demand forecasting. First, on the basis of buying intentions surveys, choose population and had produced buying demand, awareness demand, potential demand. I could estimate some profit to take out expense and cost from the buying demand. This estimated profit is marketability judgement data of product design at the design concept stage and can be utilized to measurable data for decision-making of product development. Through the case study, this method could forecast a target demand, and even if it is some difference between real sales volume, but the case study could verified that this method is effective to the evaluation of marketability in case of completely new product got on the typical category and the product category could be set up the population clearly.

• 자원ㆍ환경경제연구
• /
• 제22권1호
• /
• pp.3-29
• /
• 2013

The purpose of this study is to estimate consumer preferences on hybrid cars and electric cars by employing a choice experiment reflecting the various market conditions, such as different projected market shares of green vehicles and $CO_2$ emission regulations. Depending on different market scenarios, we examine as to which attribute and individual characteristic affect the preferences of potential consumers on green vehicles and further, forecast the potential market shares of green cars. The primary results, estimated by a conditional logit and panel probit models, indicate that sales price, fuel cost, maximum speed, emission of air pollutants, fuel economy, and distance between fuel stations can significantly affect consumer's choice of environment-friendly cars. The second finding is that the unique features of electric cars might better appeal to consumers as the market conditions for electric cars are improved. Third, education, age, and gender can significantly affect individual preferences. Finally, as the market conditions become more favorable toward green cars, the forecasted market shares of hybrid and electric vehicles will increase up to 67% and 14%.

• 산업경영시스템학회지
• /
• 제43권3호
• /
• pp.61-67
• /
• 2020

The fourth industrial revolution encourages manufacturing industry to pursue a new paradigm shift to meet customers' diverse demands by managing the production process efficiently. However, it is not easy to manage efficiently a variety of tasks of all the processes including materials management, production management, process control, sales management, and inventory management. Especially, to set up an efficient production schedule and maintain appropriate inventory is crucial for tailored response to customers' needs. This paper deals with the optimized inventory policy in a steel company that produces granule products under supply contracts of three targeted on-time delivery rates. For efficient inventory management, products are classified into three groups A, B and C, and three differentiated production cycles and safety factors are assumed for the targeted on-time delivery rates of the groups. To derive the optimized inventory policy, we experimented eight cases of combined safety stock and data analysis methods in terms of key performance metrics such as mean inventory level and sold-out rate. Through simulation experiments based on real data we find that the proposed optimized inventory policy reduces inventory level by about 9%, and increases surplus production capacity rate, which is usually used for the production of products in Group C, from 43.4% to 46.3%, compared with the existing inventory policy.

• 산업공학
• /
• 제18권2호
• /
• pp.205-220
• /
• 2005

This study presents a web log analysis model for e-CRM, which combines the on-line customer's purchasing pattern data and transaction data between companies in B2B environment of make-to-order company. With this study, the customer evaluation and the customer subdivision are available. We can forecast the estimate demands with periodical products sales records. Also, the purchasing rate per each product, the purchasing intention rate, and the purchasing rate per companies can be used as the basic data for the strategy for receiving the orders in future. These measures are used to evaluate the business strategy, the quality ability on products, the customer's demands, the benefits of customer and the customer's loyalty. And it is used to evaluate the customer's purchasing patterns, the response analysis, the customer's secession rate, the earning rate, and the customer's needs. With this, we can satisfy various customers' demands, therefore, we can multiply the company's benefits. And we presents case of the 'H' company, which has the make-to-order manufacture environment, in order to verify the effect of the proposal system.

• 산업경영시스템학회지
• /
• 제46권2호
• /
• pp.152-159
• /
• 2023

Due to COVID-19, changes in consumption trends are taking place in the distribution sector, such as an increase in non-face-to-face consumption and a rapid growth in the online shopping market. However, it is difficult for small and medium-sized export sellers to obtain forecast information on the export market by country, compared to large distributors who can easily build a global sales network. This study is about the prediction of export amount and export volume by country and item for market information analysis of small and medium export sellers. A prediction model was developed using Lasso, XGBoost, and MLP models based on supervised learning and deep learning, and export trends for clothing, cosmetics, and household electronic devices were predicted for Korea's major export countries, the United States, China, and Vietnam. As a result of the prediction, the performance of MAE and RMSE for the Lasso model was excellent, and based on the development results, a market analysis system for small and medium sellers was developed.

• 조명전기설비학회논문지
• /
• 제22권2호
• /
• pp.63-70
• /
• 2008

본 논문은 현 배전계통계획시스템(DISPLAN)의 지역전력수요예측 알고리즘을 개선하여 다중회귀분석을 이용한 지역전력수요예측 알고리즘을 제시하였다. 지역전력수요예측 알고리즘은 예측의 정확도를 높이기 위해 지역경제와 지역인구와 과거의 판매전력량을 입력변수로 사용하였다. 사례연구로 경북의 경산시, 구미시, 김천시, 영주시를 선정하여 제안한 방법의 정확도를 분석하였다. 사례연구 결과 제안한 방법의 전반적인 정확도는 11.2[%]로 DISPLAN의 12[%]보다 향상되었다. 특히 입력변수의 변동성이 심한 지역의 경우에서 많이 개선되었다. 제안된 방법은 배전계통시스템의 최적투자를 위한 지역전력수요예측에 사용될 것으로 사료된다.

• Journal of the Korean Data and Information Science Society
• /
• 제28권2호
• /
• pp.287-295
• /
• 2017

2016년 3월 구글 (Google)의 바둑인공지능 알파고 (AlphaGo)가 이세돌 9단과의 바둑대결에서 승리한 이후 다양한 분야에서 인공지능 사용에 대한 관심이 높아지고 있는 가운데 금융투자 분야에서도 인공지능과 투자자문 전문가의 합성어인 로보어드바이저 (Robo-Advisor)에 대한 관심이 높아지고 있다. 인공지능 (artificial intelligence)기반의 의사결정은 비용 절감은 물론 효과적인 의사결정을 가능하게 한다는 점에서 큰 장점이 있다. 본 연구에서는 기술적 분석 (technical analysis) 지표와 딥러닝 (deep learning) 모형을 결합하여 한국 코스피 지수를 예측하는 모형을 개발하고 제시한 모형들의 예측력을 비교, 분석한다. 분석 결과 기술적 분석 지표에 딥러닝 알고리즘을 결합한 모형이 주가지수 방향성 예측 문제에 응용될 수 있음을 확인하였다. 향후 본 연구에서 제안된 기술적 분석 지표와 딥러닝모형을 결합한 기법은 로보어드바이저서비스에 응용할 수 있는 일반화 가능성을 보여준다.