Investment Support System using the EVOLINO Recurrent Neural Network Ensemble

Algirdas Maknickas, Nijolė Maknickienė


The chaotic and largely unpredictable conditions that prevail in exchange markets are of considerable interest to speculators because of the potential for profit. The creation and development of a support system using artificial intelligence algorithms provides new opportunities for investors in financial markets. Therefore, the authors have developed a support system that processes historical data, makes predictions using an ensemble of EVOLINO recurrent neural networks, assesses these predictions using a composition of high-low distributions, selects an orthogonal investment portfolio, and verifies the outcome on the real market. The support system requires multi-core hardware resources to allow for timely data processing using an MPI library-based parallel computation approach. A comparison of daily and weekly predictions reveals that weekly forecasts are less accurate than daily predictions, but are still accurate enough to trade successfully on the currency markets. Information obtained from the support system gives investors an advantage over uninformed market players in making investment decisions.


  1. Asgharian, H. (2011). A conditional asset-pricing model with the optimal orthogonal portfolio. Journal of Banking & Finance, 35(5):1027-1040.
  2. Asgharian, H. and Hansson, B. (2005). Evaluating the importance of missing risk factors using the optimal orthogonal portfolio approach. Journal of Empirical Finance, 12(4):556-575.
  3. Assaad, M., Boné, R., and Cardot, H. (2008). A new boosting algorithm for improved time-series forecasting with recurrent neural networks. Information Fusion, 9(1):41-55.
  4. Caporin, M., Ranaldo, A., and De Magistris, P. S. (2013). On the predictability of stock prices: A case for high and low prices. Journal of Banking & Finance, 37(12):5132-5146.
  5. Chen, C.-W. (2014). Retracted: Applications of neuralnetwork-based fuzzy logic control to a nonlinear timedelay chaotic system. Journal of Vibration and Control, 20(4):589-605.
  6. Collins, M. (2007). Ensembles and probabilities: a new era in the prediction of climate change. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 365(1857):1957- 1970.
  7. Corwin, S. A. and Schultz, P. (2012). A simple way to estimate bid-ask spreads from daily high and low prices. The Journal of Finance, 67(2):719-760.
  8. Farmer, J. D. and Sidorowich, J. J. (1987). Predicting chaotic time series. Physical review letters, 59(8):845.
  9. Felder, M., Kaifel, A., and Graves, A. (2010). Wind power prediction using mixture density recurrent neural networks. In Poster Presentation gehalten auf der European Wind Energy Conference.
  10. Fonseca, R. and Gómez-Gil, P. (2014). Temporal validated meta-learning for long-term forecasting of chaotic time series using monte carlo cross-validation. In Recent Advances on Hybrid Approaches for Designing Intelligent Systems, pages 353-367. Springer.
  11. Gers, F. A., Schmidhuber, J., and Cummins, F. (2000). Learning to forget: Continual prediction with lstm. Neural computation, 12(10):2451-2471.
  12. Goudreau, M., Giles, C., Chakradhar, S., and Chen, D. (1994). First-order vs. second-order single layer recurrent neural networks. IEEE Trans. on Neural Networks, 5(3):511.
  13. Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8):1735-1780.
  14. Maknickas, A. and Maknickiene, N. (2012). Influence of data orthogonality: on the accuracy and stability of financial market predictions. In IJCCI 2012, pages 616-619. INSTICC.
  15. Maknickiene?, N. and Maknickas, A. (2013). Financial market prediction system with evolino neural network and delphi method. Journal of Business Economics and Management, 14(2):403-413.
  16. Markowitz, H. (1952). Portfolio selection*. The journal of finance, 7(1):77-91.
  17. Markowitz, H. (1987). Mean-variance analysis in portfolio choice and capital markets. Blackwell.
  18. Markowitz, H. (2014). Mean-variance approximations to expected utility. European Journal of Operational Research, 234(2):346-355.
  19. Mayer, H., Gomez, F., Wierstra, D., Nagy, I., Knoll, A., and Schmidhuber, J. (2008). A system for robotic heart surgery that learns to tie knots using recurrent neural networks. Advanced Robotics, 22(13-14):1521-1537.
  20. McLean Sloughter, J., Gneiting, T., and Raftery, A. E. (2013). Probabilistic wind vector forecasting using ensembles and bayesian model averaging. Monthly Weather Review, 141(6):2107-2119.
  21. Roll, R. (1980). Orthogonal portfolios. Journal of Financial and Quantitative analysis, 15(05):1005-1023.
  22. Rutkauskas, A. V. (2000). Formation of adequate investment portfolio for stochasticity of profit possibilities. Property management, 4(2):100-115.
  23. Rutkauskas, A. V. and Stankevic?iene, J. (2003). Formation of an investment portfolio adequate for stochasticity of profit possibilities. Journal of Business Economics and Management, 4(1):3-12.
  24. Samanta, B. (2011). Prediction of chaotic time series using computational intelligence. Expert Systems with Applications, 38(9):11406-11411.
  25. Scharnhorst, A. and Ebeling, W. (2005). Evolutionary search agents in complex landscapes-a new model for the role of competence and meta-competence (evolino and other simulation tools). arXiv preprint physics/0511232.
  26. Schmidhuber, J., Gagliolo, M., Wierstra, D., and Gomez, F. (2005a). Evolino for recurrent support vector machines. arXiv preprint cs/0512062.
  27. Schmidhuber, J., Wierstra, D., Gagliolo, M., and Gomez, F. (2007). Training recurrent networks by evolino. Neural Computation, 19(3):757-779.
  28. Schmidhuber, J., Wierstra, D., and Gomez, F. (2005b). Evolino: Hybrid neuroevolution/optimal linear search for sequence prediction. In In Proceedings of the 19th International Joint Conference on Artificial Intelligence IJCAI. Citeseer.
  29. Sheng, C., Zhao, J., Wang, W., and Leung, H. (2013). Prediction intervals for a noisy nonlinear time series based on a bootstrapping reservoir computing network ensemble. Neural Networks and Learning Systems, IEEE Transactions on, 24(7):1036-1048.
  30. Stankevic?iene, J., Maknickiene, N., and Maknickas, A. (2014). Investigation of exchange market prediction model based on high-low daily data. In The 8th international scientific conference ”Business and Management 2014”. Vilnius.Technika.
  31. Tsai, C.-F. and Wu, J.-W. (2008). Using neural network ensembles for bankruptcy prediction and credit scoring. Expert Systems with Applications, 34(4):2639-2649.
  32. Wierstra, D., Gomez, F. J., and Schmidhuber, J. (2005). Modeling systems with internal state using evolino. In Proceedings of the 7th annual conference on Genetic and evolutionary computation, pages 1795- 1802. ACM.
  33. Zhang, G. P., Berardi, V., et al. (2001). Time series forecasting with neural network ensembles: an application for exchange rate prediction. Journal of the Operational Research Society, 52(6):652-664.

Paper Citation

in Harvard Style

Maknickas A. and Maknickienė N. (2015). Investment Support System using the EVOLINO Recurrent Neural Network Ensemble . In Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 3: NCTA, (ECTA 2015) ISBN 978-989-758-157-1, pages 138-145. DOI: 10.5220/0005600901380145

in Bibtex Style

author={Algirdas Maknickas and Nijolė Maknickienė},
title={Investment Support System using the EVOLINO Recurrent Neural Network Ensemble},
booktitle={Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 3: NCTA, (ECTA 2015)},

in EndNote Style

JO - Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 3: NCTA, (ECTA 2015)
TI - Investment Support System using the EVOLINO Recurrent Neural Network Ensemble
SN - 978-989-758-157-1
AU - Maknickas A.
AU - Maknickienė N.
PY - 2015
SP - 138
EP - 145
DO - 10.5220/0005600901380145