Building Multi-Factor Stock Selection Models Using Balanced Split Regression Trees with Sorting Normalization and Hybrid Variables

doi:10.1504/IJFIP.2015.070081

淡江大學機構典藏 > 工學院 > 土木工程學系暨研究所 > 期刊論文 > Item 987654321/104666

請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/104666

題名:	Building Multi-Factor Stock Selection Models Using Balanced Split Regression Trees with Sorting Normalization and Hybrid Variables
作者:	Yeh, I-Cheng;Lien, Che-hui;Ting, Tao-Ming
關鍵詞:	stock markets;stock selection models;multi-factor selection models;balanced split regression trees;sorting normalisation;hybrid variables;Taiwan;modelling;bull markets;bear markets
日期:	2015-06-30
上傳時間:	2016-01-06 11:06:34 (UTC+8)
摘要:	This research employed regression trees to build the predictive models of the rate of return of the portfolio and conducted an empirical study in the Taiwan stock market. Our study employed the sorting normalisation approach to normalise independent and dependent variables and used balanced split regression trees to improve the defects of the traditional regression trees. The results show (a) using the sorting normalised independent and dependent variables can build a predictive model with a better capability in predicting the rate of return of the portfolio, (b) the balanced split regression trees perform well except in the training period from 1999 to 2000. One possible reason is that the dot-com bubble achieved its peak in 2000 which changes investors' behaviour, (c) during the training period, the predictive ability of the model using data from the bull market outperforms the model using data from the bear market.
關聯:	International Journal of Foresight and Innovation Policy 10(1), pp.48-74
DOI:	10.1504/IJFIP.2015.070081
顯示於類別:	[土木工程學系暨研究所] 期刊論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
5.C.H.Lien-2015-01.pdf		457Kb	Adobe PDF	1	檢視/開啟
index.html		0Kb	HTML	229	檢視/開啟

在機構典藏中所有的資料項目都受到原著作權保護.

TAIR相關文章

資料載入中.....