Page 8 - Fister jr., Iztok, Andrej Brodnik, Matjaž Krnc and Iztok Fister (eds.). StuCoSReC. Proceedings of the 2019 6th Student Computer Science Research Conference. Koper: University of Primorska Press, 2019
P. 8
00 LSTM 600
12000 PASSIVE 500
10000
8000Portfolio value 400
6000 Number of stocks
4000 300
2000
200
00
100
100 200 300 400 500 600 7000
Trading days
Figure 3: Comparison between the automated MTS with LSTM trading strategy and passive trading strategy.
only. We conclude that either stock is inefficient, or the flood forecasting. Water, 11(7):1387, 2019.
technical analysis is indeed a very efficient tool. We agree
that arbitrage opportunities are partly conditional to the [9] L. Lin, S. Gong, T. Li, and S. Peeta. Deep
level of volatility of stock prices, since the higher the volatil- learning-based human-driven vehicle trajectory
ity, the higher the arbitrage opportunities. Volatility to its prediction and its application for platoon control of
nature comes with constant reception of new information – connected and autonomous vehicles. In The
the EMH states that stock prices quickly adjust to new infor- Autonomous Vehicles Symposium, volume 2018, 2018.
mation. If new information is constantly received, volatility
is necessarily implied as well. For future work, we would like [10] B. G. Malkiel. The efficient market hypothesis and its
to implement a multi-stock MTS with LSTMs. Instead of critics. Journal of economic perspectives, 17(1):59–82,
single-stock returns, we would like to examine the portfolio 2003.
returns. For example, German stocks in stock index DAX30
would be suitable for such an analysis. [11] S. L. Oh, E. Y. Ng, R. San Tan, and U. R. Acharya.
Automated diagnosis of arrhythmia using combination
6. REFERENCES of cnn and lstm techniques with variable length heart
beats. Computers in biology and medicine,
[1] J. Brownlee. Long Short-term Memory Networks with 102:278–287, 2018.
Python: Develop Sequence Prediction Models with
Deep Learning. Jason Brownlee, 2017. [12] L. H. Pedersen. Efficiently inefficient: how smart
money invests and market prices are determined.
[2] Z. Ding, R. Xia, J. Yu, X. Li, and J. Yang. Densely Princeton University Press, 2015.
connected bidirectional lstm with applications to
sentence classification. In CCF International [13] H. Shin and S. Y. Sohn. Segmentation of stock trading
Conference on Natural Language Processing and customers according to potential value. Expert systems
Chinese Computing, pages 278–287. Springer, 2018. with applications, 27(1):27–33, 2004.
[3] E. F. Fama. Efficient capital markets: A review of [14] V. Sˇonje, D. Alajbeg, and Z. Bubaˇs. Efficient market
theory and empirical work. The journal of Finance, hypothesis: is the croatian stock market as (in)
25(2):383–417, 1970. efficient as the us market. Financial theory and
practice, 35(3):301–326, 2011.
[4] D. Fister, J. Mun, V. Jagriˇc, and T. Jagriˇc. Deep
learning for stock market trading: A superior trading [15] R. Vinayakumar, K. Soman, P. Poornachandran, and
strategy? Neural Network World, 29(3):151–171, 2019. S. Sachin Kumar. Detecting android malware using
long short-term memory (lstm). Journal of Intelligent
[5] F. A. Gers, J. Schmidhuber, and F. Cummins. & Fuzzy Systems, 34(3):1277–1288, 2018.
Learning to forget: Continual prediction with lstm.
1999. [16] B. W. Weber. Screen-based trading in futures
markets: recent developments and research
[6] S. Hochreiter and J. Schmidhuber. Long short-term propositions. In Proceedings of the 32nd Annual
memory. Neural computation, 9(8):1735–1780, 1997. Hawaii International Conference on Systems Sciences.
1999. HICSS-32. Abstracts and CD-ROM of Full
[7] D. P. Kingma and J. Ba. Adam: A method for Papers, pages 10–pp. IEEE, 1999.
stochastic optimization. arXiv preprint
arXiv:1412.6980, 2014. [17] Y. Wu, M. Yuan, S. Dong, L. Lin, and Y. Liu.
Remaining useful life estimation of engineered systems
[8] X.-H. Le, H. V. Ho, G. Lee, and S. Jung. Application using vanilla lstm neural networks. Neurocomputing,
of long short-term memory (lstm) neural network for 275:167–179, 2018.
StuCoSReC Proceedings of the 2019 6th Student Computer Science Research Conference 8
Koper, Slovenia, 10 October
12000 PASSIVE 500
10000
8000Portfolio value 400
6000 Number of stocks
4000 300
2000
200
00
100
100 200 300 400 500 600 7000
Trading days
Figure 3: Comparison between the automated MTS with LSTM trading strategy and passive trading strategy.
only. We conclude that either stock is inefficient, or the flood forecasting. Water, 11(7):1387, 2019.
technical analysis is indeed a very efficient tool. We agree
that arbitrage opportunities are partly conditional to the [9] L. Lin, S. Gong, T. Li, and S. Peeta. Deep
level of volatility of stock prices, since the higher the volatil- learning-based human-driven vehicle trajectory
ity, the higher the arbitrage opportunities. Volatility to its prediction and its application for platoon control of
nature comes with constant reception of new information – connected and autonomous vehicles. In The
the EMH states that stock prices quickly adjust to new infor- Autonomous Vehicles Symposium, volume 2018, 2018.
mation. If new information is constantly received, volatility
is necessarily implied as well. For future work, we would like [10] B. G. Malkiel. The efficient market hypothesis and its
to implement a multi-stock MTS with LSTMs. Instead of critics. Journal of economic perspectives, 17(1):59–82,
single-stock returns, we would like to examine the portfolio 2003.
returns. For example, German stocks in stock index DAX30
would be suitable for such an analysis. [11] S. L. Oh, E. Y. Ng, R. San Tan, and U. R. Acharya.
Automated diagnosis of arrhythmia using combination
6. REFERENCES of cnn and lstm techniques with variable length heart
beats. Computers in biology and medicine,
[1] J. Brownlee. Long Short-term Memory Networks with 102:278–287, 2018.
Python: Develop Sequence Prediction Models with
Deep Learning. Jason Brownlee, 2017. [12] L. H. Pedersen. Efficiently inefficient: how smart
money invests and market prices are determined.
[2] Z. Ding, R. Xia, J. Yu, X. Li, and J. Yang. Densely Princeton University Press, 2015.
connected bidirectional lstm with applications to
sentence classification. In CCF International [13] H. Shin and S. Y. Sohn. Segmentation of stock trading
Conference on Natural Language Processing and customers according to potential value. Expert systems
Chinese Computing, pages 278–287. Springer, 2018. with applications, 27(1):27–33, 2004.
[3] E. F. Fama. Efficient capital markets: A review of [14] V. Sˇonje, D. Alajbeg, and Z. Bubaˇs. Efficient market
theory and empirical work. The journal of Finance, hypothesis: is the croatian stock market as (in)
25(2):383–417, 1970. efficient as the us market. Financial theory and
practice, 35(3):301–326, 2011.
[4] D. Fister, J. Mun, V. Jagriˇc, and T. Jagriˇc. Deep
learning for stock market trading: A superior trading [15] R. Vinayakumar, K. Soman, P. Poornachandran, and
strategy? Neural Network World, 29(3):151–171, 2019. S. Sachin Kumar. Detecting android malware using
long short-term memory (lstm). Journal of Intelligent
[5] F. A. Gers, J. Schmidhuber, and F. Cummins. & Fuzzy Systems, 34(3):1277–1288, 2018.
Learning to forget: Continual prediction with lstm.
1999. [16] B. W. Weber. Screen-based trading in futures
markets: recent developments and research
[6] S. Hochreiter and J. Schmidhuber. Long short-term propositions. In Proceedings of the 32nd Annual
memory. Neural computation, 9(8):1735–1780, 1997. Hawaii International Conference on Systems Sciences.
1999. HICSS-32. Abstracts and CD-ROM of Full
[7] D. P. Kingma and J. Ba. Adam: A method for Papers, pages 10–pp. IEEE, 1999.
stochastic optimization. arXiv preprint
arXiv:1412.6980, 2014. [17] Y. Wu, M. Yuan, S. Dong, L. Lin, and Y. Liu.
Remaining useful life estimation of engineered systems
[8] X.-H. Le, H. V. Ho, G. Lee, and S. Jung. Application using vanilla lstm neural networks. Neurocomputing,
of long short-term memory (lstm) neural network for 275:167–179, 2018.
StuCoSReC Proceedings of the 2019 6th Student Computer Science Research Conference 8
Koper, Slovenia, 10 October
