由於國際原油價格不斷攀升，加上節能、環保議題、休閒運動和樂活新興生活型態等各項因素的交互影響，使的自行車產業成為新一代的明星產業。為了順應此一趨勢，故本研究期望透過資料採礦的應用，配合SPSS Clementine 12.0軟體，冀望找出是否擁有自行車之影響變數，並以巨大捷安特以及愛地雅為個案分析對象，進行行銷組合策略分析與建議。
投入變數共分為三大部分：基本人口統計變數、生活型態變數以及自行車消費行為變數，進行模型建置，由於分類迴歸樹不論是在整體預測正確率或準確度，皆是高於羅吉斯迴歸和類神經網路，故最後選擇分類迴歸樹此一模型。
透過分類迴歸樹共獲得八項影響「是否擁有自行車」之相關變數，其中「月可支配所得」、「出生年次」、「性別」、「報紙接觸率」、「商品訴求-樂活」、「保健食品最近一年使用時間」、「親疏關係情人」、「商品訴求-排毒」，此八項變數對自行車擁有者具較大影響力，故本研究以此八項變數為巨大捷安特和愛地雅之行銷策略建議依據。 / Due to the interrelationship among the dramatic run-up in gasoline, advocacy for energy-saving issue and conservation of the earth, leisure activities, and LOHAS lifestyles, the bike industry turns out to be a leading and star industry in this era. In order to follow this trend, the study aims to discover the core factors of possessing bicycles through the application of SPSS Clementine 12.0 software.
Three variables—demographics, lifestyles and the bicycle consumption behavior—were used to construct the model. Since Decision tree-CART is excellent in the forecast accuracy and validity as compared to Logistic regression and Artificial neural network, the Decision tree-CART was adopted in this research.
Through using Decision tree-CART, this study identified eight factors that have greater impact on possessing bicycles and they are “ monthly income”, “year of the birth”, “sex (distinction)”, “The frequency of reading newspaper”, “product expectation—LOHAS”, “ The usage of health products within a year”, “the relationship with the opposite sex”, “product expectation—detoxification”. This research will chiefly use these eight factors to provide the marketing portfolio strategy recommendations for GIANT and IDEAL.
Keywords: Cycling, Data Mining, Decision tree-CART, GIANT, IDEAL, Marketing Portfolio Strategy
| Identifer | oai:union.ndltd.org:CHENGCHI/G0096355035 |
| Creators | 甘齡珺 |
| Publisher | 國立政治大學 |
| Source Sets | National Chengchi University Libraries |
| Language | 中文 |
| Detected Language | English |
| Type | text |
| Rights | Copyright © nccu library on behalf of the copyright holders |
Page generated in 0.0014 seconds