• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.201-222
• /
• 2023

As the e-Commerce gets increased based on the platform, a lot of small and medium sized sellers have tried to develop the more effective strategies to maximize the profit. In order to increase the profitability, it is quite important to make the strategic decisions based on the range of promotion, discount rate and categories of products. This research aims to develop the business intelligence application which can help sellers of e-Commerce platform make better decisions. To decide whether or not to promote, it is needed to predict the level of increase in sales after promotion. I n this research, we have applied the various machine learning algorithm such as MLP(Multi Layer Perceptron), Gradient Boosting Regression, Random Forest, and Linear Regression. Because of the complexity of data structure and distinctive characteristics of product categories, Random Forest and MLP showed the best performance. It seems possible to apply the proposed approach in this research in support the small and medium sized sellers to react on the market changes and to make the reasonable decisions based on the data, not their own experience.

• Fire Science and Engineering
• /
• v.32 no.6
• /
• pp.55-62
• /
• 2018

To improve the prediction result with enhanced reliability of domestic Performance-Based Design (PBD), actual scale fire tests were carried out on products made of plastics from sales facility combustibles. The commercial buildings were separated into single and multiple combustibles for the experimentation of fire spread caused by the sales shelves where the various combustible materials are displayed. A according to the maximum heat release rate, exposed area and weight of the combustible material, the results revealed a linear relationship of as 93% and 89%. In addition, analysis of the gas concentrations for various combustibles showed that $CO_2$ has a linear relationship, whereas the CO concentration indicated exponential function. These results can be applied to reliable fire source information in PBD of plastic fire source in commercial buildings. This may be applied as fire source information representative of a plastic fire in commercial buildings through additional experiment using the area of the shelf in actual commercial buildings.

• Journal of Digital Convergence
• /
• v.19 no.11
• /
• pp.445-456
• /
• 2021

The purpose of this study is to identify the importance of variables affecting women's golf wear sales with macroeconomic variables and consumer selling prices that affect consumers' purchasing behavior, and to propose a price strategy to increase sales of golf wear. Data of domestic women's golf wear brands were analyzed using decision tree algorithms and ensemble. Consumer selling price is the most significant factors in terms of sales volume for T-shirt, pants and knit, while categories were found to be the most important factors in addition to consumer sales prices for skirt and one piece dress. These findings suggest that items have different economic variables that affect consumers' purchasing behavior, suggesting that sales and profits can be maximized through appropriate price strategies.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.5
• /
• pp.91-95
• /
• 2002

Electronic commerce over the Internet is predicted to grow at an ever-increasing rate over the next few years, with on-line sales already heading for several billion. Many companies are using this new sales channel, and a few retailers now have established major on-line sales sites. There have been some successes, particularly in technology, business-to-business and niche markets. This paper has been produced to summarise the basics of electronic commerce system, covering on-line catalogues and on-line purchasing. Electronic commerce systems consists of the authoring tools and web applications, the electronic payment technology, and the security and transaction processing.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.04a
• /
• pp.465-468
• /
• 2001

현재 전자상거래에서의 이용률이 저조한 경매시스템을 지능적인 소프트웨어 에이전트를 이용하여 사용자 측면에서 더욱 효율적이고 효과적인 경매시스템을 연구 및 개발은 커다란 이슈가 되고 있다. 따라서, 단순한 게시판 형식의 인터넷 경매 시스템의 인공지능 에이전트를 도입하여 해당 경매 상품에 대해 판매자에게 적정한 경매 시기와 초기값을 계산 및 예측하여 최대한의 마진을 남길 수 있도록 해주는 에이전트 시스템의 연구가 본 논문의 목적이다. 상품을 인터넷 경매에 올리는 판매자가 판매 하고자 하는 경매 상품에 대한 정보를 인터넷 경매 시스템의 에이전트에게 메일로 보내면 에이전트는 해당 상품과 유사한 상품에 대해 필터링하여 이미 학습되어져 있는 유사 상품에 대한 정보 즉, 데이터베이스에 저장되어 있는 경매 상품에 대한 입찰 히스토리와 경매시간, 경매방법, 낙찰가격 등을 계산하여 해당 상품에 대해 판매자가 어느 시기에 얼마의 초기 가격으로 경매를 시작하면 최대한의 마진을 남길 수 있는지에 대해 정보를 메일로 푸쉬해 주는 시스템을 설계 및 구현한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.173-178
• /
• 2023

As Korean literature spreads around the world, its position in the overseas publishing market has become important. As demand in the overseas publishing market continues to grow, it is essential to predict future book sales and analyze the characteristics of books that have been highly favored by overseas readers in the past. In this study, we proposed ensemble learning based prediction model and analyzed characteristics of the cumulative sales of more than 5,000 copies classified as good sellers published overseas over the past 5 years. We applied the five ensemble learning models, i.e., XGBoost, Gradient Boosting, Adaboost, LightGBM, and Random Forest, and compared them with other machine learning algorithms, i.e., Support Vector Machine, Logistic Regression, and Deep Learning. Our experimental results showed that the ensemble algorithm outperforms other approaches in troubleshooting imbalanced data. In particular, the LightGBM model obtained an AUC value of 99.86% which is the best prediction performance. Among the features used for prediction, the most important feature is the author's number of overseas publications, and the second important feature is publication in countries with the largest publication market size. The number of evaluation participants is also an important feature. In addition, text mining was performed on the four book reviews that sold the most among good-selling books. Many reviews were interested in stories, characters, and writers and it seems that support for translation is needed as many of the keywords of "translation" appear in low-rated reviews.

• The Journal of Society for e-Business Studies
• /
• v.19 no.1
• /
• pp.119-129
• /
• 2014

The renowned Pareto rule of 80/20 has been challenged in the electronic marketplace with the emergence of long tail economy. Mass customization on top of the Internet infrastructure is expected to explain these changes of product concentration. In this paper, we empirically analyzed the micro-transactional data of a Groupon-like daily deal web site to identify the changes of product and customer concentration. The results show the long tail pattern aligned with the previous research on the e-commerce literature on the long tail. We find that the notification setting on email or SMS about daily deal influences the patterns of sales concentration. The information through email and SMS is expected to enable consumers to know about daily bargains and purchase the coupons eventually. However, the email notification for niche products results in the decreased sales while the SMS notification for overall product promotes overall products.

• Smart Media Journal
• /
• v.11 no.4
• /
• pp.19-29
• /
• 2022

Recently, with the development of IoT technology, the number of farms using smart farms is increasing. Smart farms monitor the environment and optimise internal environment automatically to improve crop yield and quality. For optimized crop cultivation, researches on predict crop productivity are actively studied, by using collected agricultural digital data. However, most of the existing studies are based on statistical models based on existing statistical data, and thus there is a problem with low prediction accuracy. In this paper, we use various predition models for predicting the production and sales profits, and compare the performance results through models by using the agricultural digital data collected in the facility horticultural smart farm. The models that compared the performance are multiple linear regression, support vector machine, artificial neural network, recurrent neural network, LSTM, and ConvLSTM. As a result of performance comparison, ConvLSTM showed the best performance in R2 value and RMSE value.

• The Optical Journal
• /
• s.123
• /
• pp.36-37
• /
• 2009

전세계적으로 불어 닥친 경제불황은 일본을 비롯한 외국의 글로벌 제조사가 에측한 것 이상으로 심각한 직격탄을 날렸다. 2007년부터 2008년 가을까지 출하대수, 출하금액 모두 전년실적을 상회했던 프로덕션 디지털기로 2008년 가을 이후 그 기세를 급속히 잃어가고 있다. 그 큰 이유가 저조한 경기로 의한 신규 IT 투자의 삭감에 있는 만큼 2009년의 성장성도 큰 기대는 할 수 없을 것으로 보인다. 흑백기기의 2009년 판매대수 예측은 경제불황의 영향으로 전년비 성장률이 마이너스이지만, 컬러기기 시장보다는 하락폭이 작은 -7.8%에 머물 것으로 보인다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2001.10a
• /
• pp.69-71
• /
• 2001

서비스 품질의 향상을 기하기 위해서는 제품의 고장에 따른 부품의 적시 공급이 매우 중요하다. 이를 위해서는 항시 서비스 부품의 수요를 어느 정도 정확히 예측해야 한다. 본 논문은 주 제품(prime product)에 부분 의존적인 서비스 부품의 수요 예측 방법을 제시한다. 부분 종속적인 서비스 부품은 특정 부품이 장착되는 주 부품이 여러 개인 경우를 지칭한다. 기존의 방법은 주로 판매되는 부품의 수량에 의거하여 미래의 부품 수요량을 예측하는 단순 시계열이나 수요 확산 및 대체 모형에 근거하고 있는 실정이다. 본 논문은 주 제품의 폐기율과 부품의 고장율의 추정을 통한 부품의 수요 예측 방법을 제시한다. 부품 수요에 대한 다양한 수식 개발을 통해 부품 수요의 구간 추정식이 제시된다. 또한 주 제품에 장착되는 부품의 고장율이 주 제품에 무관하다는 가정하에 부품의 총 수요를 추정하는 절차를 제시하고 시뮬레이션을 통해 이러한 가정의 타당성을 고찰한다.