Using Mixture Design and Neural Networks to Build Stock Selection Decision Support Systems

doi:10.1007/s00521-015-2090-x

機構典藏 > College of Engineering > Graduate Institute & Department of Civil Engineering > Journal Article > Item 987654321/106190

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/106190

Title:	Using Mixture Design and Neural Networks to Build Stock Selection Decision Support Systems
Authors:	Yi-Cheng Liu;I-Cheng Yeh
Keywords:	Neural networks;design of experiments;multi-factor;weighted scoring;stock selection
Date:	2015-11-16
Issue Date:	2016-04-22 13:23:46 (UTC+8)
Publisher:	Springer London
Abstract:	There are three disadvantages of weighted scoring stock selection models. First, they cannot identify the relations between weights of stock-picking concepts and performances of portfolios. Second, they cannot systematically discover the optimal combination for weights of concepts to optimize the performances. Third, they are unable to meet various investors’ preferences. This study aims to more efficiently construct weighted scoring stock selection models to overcome these disadvantages. Since the weights of stock-picking concepts in a weighted scoring stock selection model can be regarded as components in a mixture, we used the simplex centroid mixture design to obtain the experimental sets of weights. These sets of weights are simulated with US stock market historical data to obtain their performances. Performance prediction models were built with the simulated performance data set and artificial neural networks. Furthermore, the optimization models to reflect investors’ preferences were built up, and the performance prediction models were employed as the kernel of the optimization models so that the optimal solutions can now be solved with optimization techniques. The empirical values of the performances of the optimal weighting combinations generated by the optimization models showed that they can meet various investors’ preferences and outperform those of S&P’s 500 not only during the training period but also during the testing period.
Relation:	Neural Computing and Applications 28(3), p.521-535
DOI:	10.1007/s00521-015-2090-x
Appears in Collections:	[Graduate Institute & Department of Civil Engineering] Journal Article

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	349	View/Open

Loading...