Portfolio Investment Based on Neural Networks

Created by W.Langdon from gp-bibliography.bib Revision:1.7642

@MastersThesis{Jia-Hong_Liu:thesis,

• author = "Jia-Hong Liu",
• title = "Portfolio Investment Based on Neural Networks",
• school = "Department of Computer Science and Engineering, National Sun Yat-sen University",
• year = "2018",
• address = "Kaohsiung, Taiwan",
• month = jul # "~21",
• note = "Master Thesis",
• keywords = "genetic algorithms, genetic programming, gene expression programming, neural network, ANN, stock investment, convolutional neural network, portfolio",
• language = "en",
• contributor = "Shih-Chung Chen and Chiou-Yi Hor and Chien-Feng Huang and Chang-Biau Yang",
• oai = "oai:NSYSU:etd-0621118-142449",
• rights = "user_define; Copyright information available at source archive",
• URL = "http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0621118-142449",
• URL = "http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/getfile?URN=etd-0621118-142449&filename=etd-0621118-142449.pdf",
• size = "56 pages",
• abstract = "In this thesis, we combine the trading signals generated by the gene expression programming (GEP) method of Lee et al. and the portfolio generated by convolutional neural network (CNN) structure of Jiang et al. to form a stock investment method with portfolio management. The method of Jiang et al. focuses on the investment of the cryptocurrency. We change the invested target of Jiang et al. from cryptocurrency to stocks. We recompute the weights of the portfolio when the method of Lee et al. generates a trading signal (buy or sell). To test our method, we choose 213 stocks which always exist during 1995/1/5 to 2017/12/29 on stock market in Taiwan. Our training period starts from 1995/1/5. We perform the trading from 2002/1/2 until 2017/12/29. There are three cases in our experiments: Trading 100 stocks with the 100-stock features, trading 100 stocks with the 213-stock features, and trading 213 stocks with the 213-stock features. The annualized returns for the three cases are 25.00percent, 26.52percent and 27.32percent, respectively. Our method is better than the buy-and-hold 12.36percent for 100 stocks, and 12.21percent for 213 stocks. Our method is also better than the method of Lee et al. without portfolio management 12.94percent for 100 stocks, and 12.67percent for 213 stocks.",
• notes = "NSYSU",

}

Genetic Programming entries for Jia-Hong Liu

Citations