Deep stock representation learning: from candlestick charts to investment decisions

Guosheng Hu, Yuxin Hu, Kai Yang, Zehao Yu, Flood Sung, Zhihong Zhang, Fei Xie, Jianguo Liu, Neil Robertson, Timothy Hospedales, Qiangwei Miemie

Research output: Contribution to conferencePaper

160 Downloads (Pure)

Abstract

We propose a novel investment decision strategy (IDS) based on deep learning. The performance of many IDSs is affected by stock similarity. Most existing stock similarity measurements have the problems: (a) The linear nature of many measurements cannot capture nonlinear stock dynam- ics; (b) The estimation of many similarity metrics (e.g. co- variance) needs very long period historic data (e.g. 3K days) which cannot represent current market effectively; (c) They cannot capture translation-invariance. To solve these prob- lems, we apply Convolutional AutoEncoder to learn a stock representation, based on which we propose a novel portfolio construction strategy by: (i) using the deeply learned repre- sentation and modularity optimisation to cluster stocks and identify diverse sectors, (ii) picking stocks within each clus- ter according to their Sharpe ratio (Sharpe 1994). Overall this strategy provides low-risk high-return portfolios. We use the Financial Times Stock Exchange 100 Index (FTSE 100) data for evaluation. Results show our portfolio outperforms FTSE 100 index and many well known funds in terms of total return in 2000 trading days.
Original languageEnglish
Publication statusAccepted - 26 Jan 2018
EventIEEE International Conference on Acoustics, Speech and Signal Processing - Calgary, Calgary, Canada
Duration: 15 Jan 201820 Jan 2018
Conference number: 2018
https://2018.ieeeicassp.org/
https://2018.ieeeicassp.org

Conference

ConferenceIEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated titleICASSP
CountryCanada
CityCalgary
Period15/01/201820/01/2018
Internet address

Fingerprint Dive into the research topics of 'Deep stock representation learning: from candlestick charts to investment decisions'. Together they form a unique fingerprint.

Cite this