探索汽油價格變動對消費者選擇產品之影響 -以某超級市場為例;Investigating the effect of gas price on purchase of consumer products

NCUIR > School of Management at National Central University > Graduate Institute of Business Administration > Electronic Thesis & Dissertation > Item 987654321/76935

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/76935

Title:	探索汽油價格變動對消費者選擇產品之影響 -以某超級市場為例;Investigating the effect of gas price on purchase of consumer products
Authors:	劉世閎;LIU, SHIH-HUNG
Contributors:	企業管理學系
Keywords:	油價;線性回歸;資料探勘;皮爾森相關積差分析;gas price;linear regression;data mining;Pearson Correlation
Date:	2018-07-27
Issue Date:	2018-08-31 11:53:48 (UTC+8)
Publisher:	國立中央大學
Abstract:	本論文之研究主要探討台灣地區汽油價格變動對消費者選擇產品之影響。目前現有論文研究主要著重在油價變動對總體經濟之影響，例如股價、消費者物價指數,消費者信心指數等相關經濟指標之影響，尚未有論文研究油價對個體經濟之影響。本文研究石油價格對消費者選擇產品之影響，採用使用台灣某中型超級市場其中一家分店2002年度之顧客交易資料，並利用Pearson相關績差分析找出銷售數量與汽油油價有顯著相關之類別產品，再利用線性回歸模型找出產品價格與油價對其類別銷售數量之回歸方程式。本研究找到三個大類別,五類個中類別,二十一個小類別與油價呈現顯著相關，並找到19個小類別之線性回歸方程式來預測其銷售數量，且本研究只需要每筆交易之產品編號及數量就可進行資料分類處理及分析，對比以往先關資料探勘方法更有相當的貢獻。 ;The research in this paper mainly discusses the effect of gas price purchase of consumer products in Taiwan. At present, the existing research focuses on the impact of gas price changes on the macroeconomics, such as stock price, consumer price index, consumer confidence index and other relevant macroeconomic indicators. There is no research to study the impact of changes in gas prices on microeconomics. The data is usd from one of medium-sized supermarket in Taiwan in 2002.Uses Pearson Correlation to find out the product category which selling volume is significantly related to gas prices. Then use the linear regression model to find the regression equation of the selling volume and gas price of the category products. In this study, a total of three large categories and five categories and twenty-one small categories were found to be significantly correlated with gas prices. And found nineteen small categories of linear regression equations to predict the selling volume, and this study only needs the product number and selling volume of each transaction for data classification and analysis, compared with the previous data mining methods this paper provided an alternative comparable method of analysis.
Appears in Collections:	[Graduate Institute of Business Administration] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	207	View/Open

社群 sharing

Loading...