DC 欄位 |
值 |
語言 |
DC.contributor | 企業管理學系 | zh_TW |
DC.creator | 許哲愷 | zh_TW |
DC.creator | Che-Kai Hsu | en_US |
dc.date.accessioned | 2019-7-15T07:39:07Z | |
dc.date.available | 2019-7-15T07:39:07Z | |
dc.date.issued | 2019 | |
dc.identifier.uri | http://ir.lib.ncu.edu.tw:444/thesis/view_etd.asp?URN=106421002 | |
dc.contributor.department | 企業管理學系 | zh_TW |
DC.description | 國立中央大學 | zh_TW |
DC.description | National Central University | en_US |
dc.description.abstract | 鑒於目前研究客戶流失或變動的研究中並沒有保健食品產業,並且對於給定全部變
動以及部分變動有些並沒有明確的定義。本研究客戶變動之產業為保健食品產業,且對
於本篇研究所使用的部分變動給定一個明確的定義,讓之後研究類似產業及相同變動定
義的研究可以作為參考。加入除了研究客戶變動最重要的構面忠誠度以外的另外一個構
面—信任。使用卷積類神經網路演算法去判斷該客戶是否會產生變動。結果顯示卷積類
神經網路在預測客戶變動的準確率表現上的確優於 SVM 及驗證忠誠度三構面的重要性。
| zh_TW |
dc.description.abstract | There is no nutrient supplement industry in the current study of customer churn or change,
and there is no clear definition of total churn and partial churn. This thesis may be the first
research of the customer churn of nutrient supplement industry, and a clear definition is given
for partial churn used in this thesis. Join another facet other than the most important facet of
loyalty about customer churn research—trust. Using Convolutional Neural Network(CNN) to
determine if the customer will churn. The results show that the Convolutional Neural Network
is indeed superior to the SVM. | en_US |
DC.subject | 客戶變動 | zh_TW |
DC.subject | 客戶流失 | zh_TW |
DC.subject | 卷積類神經網路 | zh_TW |
DC.subject | 信任 | zh_TW |
DC.subject | 忠誠度 | zh_TW |
DC.subject | customer churn | en_US |
DC.subject | nutrient supplement industry | en_US |
DC.subject | trust | en_US |
DC.subject | loyalty | en_US |
DC.subject | CNN | en_US |
DC.title | 以 CNN 預測保健食品產業之客戶流失 | zh_TW |
dc.language.iso | zh-TW | zh-TW |
DC.title | Churn Prediction with CNN model in Nutrient Supplement Industry | en_US |
DC.type | 博碩士論文 | zh_TW |
DC.type | thesis | en_US |
DC.publisher | National Central University | en_US |