Stock Portfolio Management using LSTM model based on a proprietary Stock Promise Factor comprising Technical & Fundamental indicators
Keywords:
Technical & Fundamental Indicator, LSTMAbstract
Stock market predictions, be it prices or patterns, is a complex task that is both human intensive as well as computer intensive. The fact that the market is a dynamic and chaotic environment adds to the challenge. An intermittent rise or fall in a stock’s price has an important role in determining the investors’ gain because it affects the overall portfolio returns immensely. Due to this dynamic nature of the stock market, applying conventional batch processing methods is not a viable option. This leads us towards discovering a more actively managed portfolio as opposed to traditional methods like buying and holding value stocks or following the indices. While one can rely on stock market professionals, this paper proposes and reviews an artificial intelligence-based stock portfolio managing method. This paper proposes a LSTM and statistics-based technique to manage and restructure portfolios consisting of fundamental and technical indicators, in order to maximise the gains. The technique is tested for a portfolio of ten stocks over six months and the results are tabulated. A comparison with respect to final portfolio value is then performed against buying and holding stocks, Treasury Bills, and S&P 500 index
References
Fama, E. (1970). Efficient Capital Markets: A Review of Theory and Empirical Work. The Journal of Finance, 25(2), 383-417. doi:10.2307/2325486
Williams, R.J., & Zipser, D. (1989). A Learning Algorithm for Continually Running Fully Recurrent Neural Networks. Neural Computation, 1, 270-280.
S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997. [Online]. Available:
http://dx.doi.org/10.1162/neco.1997.9.8.1735
K. Greff, R. K. Srivastava, J. Koutnık, B. R. Steunebrink, and J. Schmidhuber, “LSTM: A search space odyssey,” arXiv preprint arXiv:1503.04069, 2015.
Felix A. Gers, J ̈urgen Schmidhuber, and Fred Cummins. Learning to forget:Continual prediction with LSTM.Neural computation, 12(10):2451–2471,2000.
B. Bengio, Y., Simard, P., and Frasconi, P. Learning long-term dependencies with gradient descent is difficult.IEEE Transactions on Neural Networks, 5(2):157–166, 1994.
A. E. Biondo, A. Pluchino, A. Rapisarda, and D. Helbing, “Are Random Trading Strategies More Successful than Technical Ones?” PLoS ONE, vol. 8, p. e68344, Jul. 2013.
Neely, Christopher J. and Rapach, David and Tu, Jun and Zhou, Guofu, Forecasting the Equity Risk Premium: The Role of Technical Indicators (April 11, 2011). Available at SSRN: https://ssrn.com/abstract=178755
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Re-users must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. This license allows for redistribution, commercial and non-commercial, as long as the original work is properly credited.
