• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.10
• /
• pp.2818-2839
• /
• 2024

With the continuous growth of e-commerce sales, a robust product selection model is essential to maintain competitiveness and meet consumer demand. Current research primarily focuses on single models for sales prediction and lacks an integrated approach to sales forecasting and product selection. This paper proposes a comprehensive framework (VN-CPC) that combines sales forecasting with product selection to address these issues. We integrate a series of classical machine learning models, including Tree Models (XGBoost, LightGBM, CatBoost), Support Vector Machine (SVM), Bayesian Ridge, and Artificial Neural Networks (ANN), using a voting mechanism to determine the optimal weighting scheme. Our method demonstrates a lower Root Mean Square Error (RMSE) on collected Amazon data than individual models and other ensemble models. Furthermore, we employ a three-tiered clustering model: Initial Clustering, Refinement Clustering, and Final Clustering, based on our predictive model to refine product selection to specific categories. This integrated forecasting and selection framework can be more effectively applied in the dynamic e-commerce environment. It provides a robust tool for businesses to optimize their product offerings and stay ahead in a competitive market.

• Journal of Intelligence and Information Systems
• /
• v.8 no.2
• /
• pp.159-175
• /
• 2002

Web mining is an emerging science of applying modem data mining technologies to the problem of extracting valid, comprehensible, and actionable information from large databases of web in e-Business environment and of using it to make crucial e-Business decisions. In this paper, we present the noble framework of data visualization system based on web mining for analyzing the characteristics of on-line customers in e-Business. We also propose the framework of forecasting system for providing the forecasting information of sales/purchase through the use of web mining based on artificial intelligence techniques such as back-propagation network, memory-based reasoning, and self-organizing map.

• Journal of Distribution Research
• /
• v.6 no.1
• /
• pp.22-35
• /
• 2001

The focus of Business Process Re-engineering (BPR) has been extended to inter-business process that cuts across independent companies. Combined with Supply Chain Management (SCM), inter-business process reengineering (IBPR) focuses on synchronization of business activities among trading partners to achieve performance improvements in inventory management and cycle time. This paper reviews the business process reengineering movement from the historical perspective and presents a case of inter-business process reengineering using the latest internet-based Business-to- Business (B2B) technology based on Collaborative Planning, Forecasting, and Replenishment (CPFR). The case demonstrates how CPFR technology reengineers the distribution process between Heineken USA and its distributors. As world's first implementor of web-based collaborative planning system, Heineken USA reduces cycle time from determining the customer need to delivery of the need by 50% and increases sales revenue by 10％. B2B commerce on the internet is predicted to grow from $90 billion in 1999 to $2.0 trillion in 2003. This paper provides the management with the bench-marking case on inter-business process reengineering using B2B e-commerce technology.

• Journal of Digital Contents Society
• /
• v.9 no.2
• /
• pp.295-303
• /
• 2008

With universality of e-commerce through internet, smaller online shopping malls are increased. A Smaller online shopping mall by nature lacks an extra space to load many inventory quantities. Therefore, it is difficult to response immediately with client request with traditional inventory management method. VMI has a character that supplier can control volume of inventory according to sales of seller. This paper proposes SOHO-VMI that is applied VMI into smaller online shopping mall. Proposed SOHO-VMI supports M $\times$ N structure can interact with multiple suppliers and sellers. And it uses XML/EDI for interaction with EDI documents use to legacy system. Also, This paper proposes logistics statistic prediction algorithm can adjust production and distribution volumes to supplier considering seller's product distribution information and seasonal factor.