English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  Items with full text/Total items : 97142/127787 (76%)
Visitors : 33375978      Online Users : 422
RC Version 6.0 © 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://nccur.lib.nccu.edu.tw/handle/140.119/136026


    Title: 應用資料採礦技術於證券客戶風險偏好之分析–以P公司為例
    Applying Data Mining to Analyze Risk Appetite of Investors: The case of P Securities Company
    Authors: 張紘嘉
    Chang, Hung-Chia
    Contributors: 鄭宇庭
    張紘嘉
    Chang, Hung-Chia
    Keywords: 資料採礦
    預測模型
    風險偏好
    Date: 2021
    Issue Date: 2021-07-01 21:31:27 (UTC+8)
    Abstract: 隨著科技的發展,Fintech發展日益俱進,其中智能理財平台更是國內各大金融巨擘必爭之地。根據數據預估,2018年至2022年全球自動化投資顧問資產規模每年以38.2%的速度成長,到2022年時資產規模可達1.45兆美元,顯示越來越多的投資人選擇智能理財平台這項工具當作選擇投資標的之媒介。
    因此本研究將利用P公司之客戶基本資料以及交易資料,運用資料採礦技術,輔以統計軟體,產出預測客戶風險偏好之模型。首先,依據交易金額以及購買的金融商品之報酬標準差加權平均出每一個客戶的加權平均標準差,依據此標準差將客戶分類成三群不同風險偏好:低風險群、中風險群以及高風險群;其次,結合客戶基本資料以及交易資料產出包含自變數以及應變數的分析資料,將此分析資料切分為訓練資料以及測試資料,訓練資料用於訓練機器演算法模型;測試資料則使用於檢驗該預測模型之準確率;最後,找出準確率最高之預測模型演算法。
    由結果所產出之預測模型,未來可應用於在客戶還未實際投資的情況下,依據其所填寫之基本資料以及相關問題,產出該客戶之風險偏好,企業可依據此風險偏好推薦其相對應的投資組合產品,達到精準行銷之目的。
    With the development of technology, the development of Fintech is advancing day by day. Robo-advisor is a new wealth management platform that all the major financial company actively develop. According to estimates, the asset under management of robo-advisor will grow at a rate of 38.2% annually from 2018 to 20222, and the asset scale will reach US$1.45 trillion by 2022. This phenomenon showing that more and more investors are choosing this platform as a medium for selecting investment product.
    Therefore, this research will use customer basic data and transaction data from P company, and supplemented by statistic software to produce a predicting model for predicting risk appetite from customer by data mining technology. Fist, based on the transaction amount and the standard deviation of the products purchased, calculated the weighted average standard deviation of each customer. Then according to this standard deviation, customers are classified into three groups with different risk appetite: low-risk group, medium-risk group, and high-risk group. Second, merge customer basic data and transaction data to produce analysis data including independent variable and dependent variable. Divide this data form into training data and testing data. The training data is used to train the machine learning model, and the testing data is used to evaluate the accuracy of the model. Finally, find the prediction model with the highest accuracy.
    The prediction model selected by the research results can be used to predict customer’s risk appetite before their actual investment behavior in the future. Based on the predict model results, produced by the basic information and related questions, the company can suggest corresponding investment portfolio to their customer according the predicted risk appetite and achieve the purpose of precise marketing.
    Reference: 一、中文文獻
    1.吳岱芸,2017,運用RFM模型結合資料採礦預測潛在顧客提升行銷效益–以Y藥局為例,政治大學企業管理研究所碩士論文。
    2.李宏毅,2017,什麼是深度學習–機器學習的捲土重來,數理人文雜誌。
    3.李怡,2017,資料探勘應用於航空公司之顧客分群研究,政治大學企業管理研究所碩士論文。
    4.卓越,2019,基於支持向量回歸的選股模型實證研究–以台股市場為例,政治大學金融學系研究所碩士論文。
    5.康力中,2020,機器人理財是否可有效消除投資人行為偏誤,臺北大學企業管理學系碩士論文。
    6.張力元,2018,深度學習應用於股價走勢之研究:以大陸市場為例,政治大學風險管理與保險學系研究所。
    7.張明珠,2019,淺談機器人理財在台灣未來之發展,證券暨期貨月刊 第三十七卷 第一期,頁14-25。
    8.張雅鈞,2016,人壽客群與商品搭售分析–以C人壽資料為例,政治大學企業管理研究所碩士論文。
    9.曹書華,2018,行為財務學在機器人理財顧問的運用、實務與挑戰,政治大學經營管理碩士學程碩士論文。
    10.莊子郁,2018,理財機器人於台灣理財市場之適用探討,政治大學風險管理與保險學系碩士論文。
    11.陳力新,2017,智能理財產業分析,政治大學經營管理碩士學程碩士論文。
    12.陳雅婷,2019,金融機構導入理財機器人關鍵成功因素之研究,臺北科技大學資訊與財金管理EMBA專班碩士論文。
    13.陳鴻,2021,臺灣普惠金融發展之研究:以韓國為鑑,政治大學企業管理研究所碩士論文。
    14.彭士嘉,2013,應用資料採礦技術於消費者網路使用行為之研究,政治大學企業管理研究所碩士論文。
    15.新智元,2019,2019中國人工智能獨角獸白皮書。
    16.謝邦昌、鄭宇庭、蘇志雄,2009,Data Mining概述—以Clementine 12.0為例,中華資料採礦協會。
    17.韓傳祥,2018,計量財務金融〈金融科技〉,新陸書局。

    二、英文文獻
    1.Alex J.Smola, Bemgard Scholkopf, 2004, A tutorial on Support Vector Regression, Statistics and Computing, 199-222.
    2.Alexander Kunst, 2020, RoboAdvisor usage in the U.S. 2020, Statista.
    3.Berry, Michael J.A., Linoff, Gordon S., 1997, Data Mining Techniques: For Marketing, Sales, and Customer Support, U.S.A., John Wiley & Sons, Inc.
    4.Betterment, 2021, Retrieved from https://www.betterment.com/
    5.EY, 2015, Advice Goes Virtual: How New Digital Investment Services Are Changing the Wealth Management Landscape.
    6.Krzystof, C., P. Witold & S. Roman, 1998, Data Mining: Methods for Knowledge Discovery. Kluwer Academic Publishers, Boston.
    7.Michael Nielsen, 2015, Neural Networks and Deep Learning,
    8.Statista Research Department, 2021, Assets under management of selected robo-advisors globally 2021, Statista.
    9.Statista, 2021, Retrieved from https://www.statista.com/
    10.Tom Mitchell, 1997, Machine Learning
    11.WEALTHFRONT, 2021, Retrieved from https://www.wealthfront.com/
    Description: 碩士
    國立政治大學
    企業管理研究所(MBA學位學程)
    108363049
    Source URI: http://thesis.lib.nccu.edu.tw/record/#G0108363049
    Data Type: thesis
    DOI: 10.6814/NCCU202100509
    Appears in Collections:[企業管理研究所(MBA學位學程)] 學位論文

    Files in This Item:

    File Description SizeFormat
    304901.pdf2962KbAdobe PDF0View/Open


    All items in 政大典藏 are protected by copyright, with all rights reserved.


    社群 sharing

    著作權政策宣告
    1.本網站之數位內容為國立政治大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,惟仍請適度,合理使用本網站之內容,以尊重著作權人之權益。商業上之利用,則請先取得著作權人之授權。
    2.本網站之製作,已盡力防止侵害著作權人之權益,如仍發現本網站之數位內容有侵害著作權人權益情事者,請權利人通知本網站維護人員(nccur@nccu.edu.tw),維護人員將立即採取移除該數位著作等補救措施。
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback