Methodologies for Discovering Sets of Critical Products

NCUIR > School of Management at National Central University > Graduate Institute of Business Administration > Electronic Thesis & Dissertation > Item 987654321/84947

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/84947

Title:	Methodologies for Discovering Sets of Critical Products
Authors:	黃振萬;Huang, Chen-Wan
Contributors:	企業管理學系
Keywords:	關鍵商品;數據挖掘;垂直數據庫;頻繁項目集挖掘;RFM;critical products;data mining;vertical database;frequent itemsets mining;RFM
Date:	2021-01-25
Issue Date:	2021-03-18 17:01:38 (UTC+8)
Publisher:	國立中央大學
Abstract:	在數位轉型時代，零售業者能夠識別出重要客戶與其相關之關鍵商品來提升公司營運績效至關重要。關鍵商品是重要客戶之關鍵購買項目，但在一般消費客戶群中並非具有影響性。儘管關鍵商品之銷售量可能偏低，但仍建議應持續保留在零售店內貨架上，藉以留住店家之重要客戶。過去文獻中少有研究考慮關鍵商品並找出識別模型。本研究提出一種利用垂直數據庫架構來識別出關鍵商品之改良演算法，並將該演算法應用於實際零售超市之交易數據庫，進行實驗以驗證其有效性。經過三種創新過濾條件設計，Precision rate分別達到80.55%、82.15% 與82.35％。本研究是第一個能夠結合多種過濾方法來發掘零售關鍵商品之研究。;Identifying critical products and important customers to strengthen company performance is vitally important in the digital transformation era. Critical products are itemsets that are preferred by important customers and yet not popular among ordinary customers. As a result, critical products should be kept on the shelf even if their sales volume is lower than that of other popular products. However, few studies have considered identifying critical products or their potentially valuable customer patterns. Therefore, an innovative algorithm that takes advantage of vertical databases to identify critical products was designed in this study. The proposed algorithm is applied to a transactions database of a midsize supermarket to verify the performance. The result showed that the precision of identifying critical products reached 80.55%, 82.15%, and 82.35% for three different filtering criteria. To the best of our knowledge, this dissertation is the first to use multiple filtering criteria to identify critical products.
Appears in Collections:	[Graduate Institute of Business Administration] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	201	View/Open

社群 sharing

Loading...