English  |  正體中文  |  简体中文  |  Items with full text/Total items : 74010/74010 (100%)
Visitors : 24657084      Online Users : 357
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version

    Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/84578

    Title: 基於信任與忠誠指標預測客戶在購行為的深度學習模型;Predicting Repurchase Behavior Based on Trust and Loyalty Indicators with Deep Learning Technology
    Authors: 許秉瑜
    Contributors: 企業管理學系
    Keywords: 預測再購行為;卷積神經網絡;遞歸神經網路;健康零售;信任;忠誠;predict repurchase behavior;Recurrent Neural Network;Convolutional Neural Network;health retail;trust;loyalty
    Date: 2020-12-08
    Issue Date: 2020-12-09 09:54:11 (UTC+8)
    Publisher: 科技部
    Abstract: 在過去的幾年裏,全世界的營養補充劑行業迅猛發展,而且這一趨勢還將持續。由於產品會過期,顧客往往不會在臨近的時間段購買很多相同的營養補充品。更值得註意的是,許多營養補充劑是通過電話銷售的,顧客只需打幾個電話就能被說服。因此,對這個行業來說,謹慎地將宣傳活動導向那些在不久的將來會購買商品的人是至關重要的,然而,傳統的采購預測模型很少考慮這些特性。另一方面,顧客的再購買意願也受到信任和忠誠的影響,對組織和產品高度信任和忠誠的顧客傾更向於回購。因此,該計畫試圖設計基於信任和忠誠度的指標模型,實驗與一家卓越的營養補充劑公司。利用購買和電話交談記錄建構這些指標,我們提出LSTM、CNN等多種預測模型和方法,並將對這些提出的方法的執行情況進行比較和對比。基於所提出的信任和忠誠指標,構建並驗證邏輯回歸模型。目的是確定各種信任和忠誠指標中的關鍵預測因子。這些指標可以用來改善營養補充劑公司的運營,因為這些指標的價值越高,客戶越有可能回購。根據這些指標,管理者可以建議呼叫代理商改進他們的溝通方式,提高電話營銷的有效性。 ;Over the past few years, the world has witnessed a dramatic growth in nutrition supplement industry and the trend will continue for next few years. Customers tend not to buy the same nutrition supplement at close time periods due to the product expiration days. Further complicating the issue is that many nutrition supplement are sold via telemarketing. Customers have to be persuaded in a few phone calls. As a result, carefully directing campaigning effort to those that will purchase items in the near future is critical for this industry. However, such characteristics has seldom being considered in traditional purchasing prediction models. On the other hands, customer repurchasing intention has known being affected by trust and loyalty. Customers with high trust and loyalty to organizations and products tend to make repurchases. This proposal therefore attempts to devises indicators based on trust and loyalty from purchase and telephone conversations logged in a leading nutrition supplement company. With the indicators, prediction models such as LSTM, CNN and a variety of methods will be proposed. The perform of these proposed methods will be compared and contrasted to each other. A logistic regression model will also be constructed and verified based on the proposed indicators of trust and loyalty. The purpose is to identify the key predictors among various trust and loyalty indicators. These indicators can be used to improve the operation of the nutrition supplement companies since the higher the values of the indicators, the more likelier the customers will repurchase. Based on the indicators, the mangers can advise the call agents to improve their communication styles and enhance the effectiveness of the telemarketing.
    Relation: 財團法人國家實驗研究院科技政策研究與資訊中心
    Appears in Collections:[企業管理學系] 研究計畫

    Files in This Item:

    File Description SizeFormat

    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明