A Study on Behavior Scorecard for Investors Risk Tolerance in Bank A - Compare with Different Training Set of the Prediction Model
碩士 === 輔仁大學 === 統計資訊學系應用統計碩士班 === 102 === After the financial crisis in 2008, government should protect the investors in the investment market. In order to enhance the quality of the bank's wealth management services and implement risk control. In the norms of the "Financial Consumer Prote...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2014
|
Online Access: | http://ndltd.ncl.edu.tw/handle/kxsfgg |
id |
ndltd-TW-102FJU00506019 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-102FJU005060192019-05-15T21:23:15Z http://ndltd.ncl.edu.tw/handle/kxsfgg A Study on Behavior Scorecard for Investors Risk Tolerance in Bank A - Compare with Different Training Set of the Prediction Model 國內A銀行客戶風險承受度評分卡之研究-不同抽樣比例訓練集之預測模型比較 Yih-Shyan Wu 吳懿軒 碩士 輔仁大學 統計資訊學系應用統計碩士班 102 After the financial crisis in 2008, government should protect the investors in the investment market. In order to enhance the quality of the bank's wealth management services and implement risk control. In the norms of the "Financial Consumer Protection Act ", the bank needs to understand the situation of investors in the background and assess Investors’ Risk Tolerance. The banks should evaluate the Investors’ Risk Tolerance seriously, and then financial consultants can design the combination of financial products according to Investors’ risk tolerance. It can help to enhance bank’s customer loyalty and professional image. In this study, Data were collected from Bank A by using the survey of “Personal Investment Worksheet” and the customers have purchased new the product of risk. Important variables were selected by two steps. The first step selected the significant variables by using Chi-Square Independent Test and reduced the multicollinearity in the data set by combining independent variables. The second step used the modeling data set to select 80% of the entire the modeling dataset. Resampling was done 30 times to construct 30 multinomial logistic models. The final important variables would be select if the number of voting is more than or equal to 30 times from the 30 models and Cramer’s value is more than or equal to 0.1. This study uses the modeling dataset to sample the proportion of different and get 70 samples of sub-training set to construct 70 multinomial logistic models. This study compares with the models. Finally, the behavior scorecard will be build base on multinomial logistic models. It can provid bank financial consultants refer investors' score to recommended financial products and asset allocation. Te-Hsin Liang 梁德馨 2014 學位論文 ; thesis 125 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 輔仁大學 === 統計資訊學系應用統計碩士班 === 102 === After the financial crisis in 2008, government should protect the investors in the investment market. In order to enhance the quality of the bank's wealth management services and implement risk control. In the norms of the "Financial Consumer Protection Act ", the bank needs to understand the situation of investors in the background and assess Investors’ Risk Tolerance. The banks should evaluate the Investors’ Risk Tolerance seriously, and then financial consultants can design the combination of financial products according to Investors’ risk tolerance. It can help to enhance bank’s customer loyalty and professional image.
In this study, Data were collected from Bank A by using the survey of “Personal Investment Worksheet” and the customers have purchased new the product of risk. Important variables were selected by two steps. The first step selected the significant variables by using Chi-Square Independent Test and reduced the multicollinearity in the data set by combining independent variables. The second step used the modeling data set to select 80% of the entire the modeling dataset. Resampling was done 30 times to construct 30 multinomial logistic models. The final important variables would be select if the number of voting is more than or equal to 30 times from the 30 models and Cramer’s value is more than or equal to 0.1. This study uses the modeling dataset to sample the proportion of different and get 70 samples of sub-training set to construct 70 multinomial logistic models. This study compares with the models. Finally, the behavior scorecard will be build base on multinomial logistic models. It can provid bank financial consultants refer investors' score to recommended financial products and asset allocation.
|
author2 |
Te-Hsin Liang |
author_facet |
Te-Hsin Liang Yih-Shyan Wu 吳懿軒 |
author |
Yih-Shyan Wu 吳懿軒 |
spellingShingle |
Yih-Shyan Wu 吳懿軒 A Study on Behavior Scorecard for Investors Risk Tolerance in Bank A - Compare with Different Training Set of the Prediction Model |
author_sort |
Yih-Shyan Wu |
title |
A Study on Behavior Scorecard for Investors Risk Tolerance in Bank A - Compare with Different Training Set of the Prediction Model |
title_short |
A Study on Behavior Scorecard for Investors Risk Tolerance in Bank A - Compare with Different Training Set of the Prediction Model |
title_full |
A Study on Behavior Scorecard for Investors Risk Tolerance in Bank A - Compare with Different Training Set of the Prediction Model |
title_fullStr |
A Study on Behavior Scorecard for Investors Risk Tolerance in Bank A - Compare with Different Training Set of the Prediction Model |
title_full_unstemmed |
A Study on Behavior Scorecard for Investors Risk Tolerance in Bank A - Compare with Different Training Set of the Prediction Model |
title_sort |
study on behavior scorecard for investors risk tolerance in bank a - compare with different training set of the prediction model |
publishDate |
2014 |
url |
http://ndltd.ncl.edu.tw/handle/kxsfgg |
work_keys_str_mv |
AT yihshyanwu astudyonbehaviorscorecardforinvestorsrisktoleranceinbankacomparewithdifferenttrainingsetofthepredictionmodel AT wúyìxuān astudyonbehaviorscorecardforinvestorsrisktoleranceinbankacomparewithdifferenttrainingsetofthepredictionmodel AT yihshyanwu guónèiayínxíngkèhùfēngxiǎnchéngshòudùpíngfēnkǎzhīyánjiūbùtóngchōuyàngbǐlìxùnliànjízhīyùcèmóxíngbǐjiào AT wúyìxuān guónèiayínxíngkèhùfēngxiǎnchéngshòudùpíngfēnkǎzhīyánjiūbùtóngchōuyàngbǐlìxùnliànjízhīyùcèmóxíngbǐjiào AT yihshyanwu studyonbehaviorscorecardforinvestorsrisktoleranceinbankacomparewithdifferenttrainingsetofthepredictionmodel AT wúyìxuān studyonbehaviorscorecardforinvestorsrisktoleranceinbankacomparewithdifferenttrainingsetofthepredictionmodel |
_version_ |
1719113332190871552 |