Dự báo tỉ giá ngoại tệ với mô hình học cộng đồng kết hợp giải thuật tiến hóa đa mục tiêu

  • Đinh Thị Thu Hương Đại học Thủ Dầu Một
  • Đỗ Thị Diệu My
  • Vũ Văn Trường
  • Bùi Thu Lâm


Time series forecasting is paid a considerable attention of the researchers. At present, in the field of machine learning, there are a lot of studies using artificial neural networks to construct the model of time series forecast in general, and foreign currency exchange rates forecast, in particular. However, determining the number of members of an ensemble is still debatable. This paper proposes the way of constructing a model and designing a multi-objective evolutionary algorithm in training neural networks ensembles in order to increase the diversity of the population. Two objectives of the selected model include: Mean Sum of Squared Errors - MSE and Diversity. We experimented the model on four data sets and compared three methods (single-objective, multi- objective and ensembles). The experimental results showed that the proposed model produced better in investigated cases.

Author Biography

Đinh Thị Thu Hương, Đại học Thủ Dầu Một
Giảng viên


HÀ VĂN SƠN, Giáo trình nguyên lí thống kê kinh tế, NXB Thống kê, 2010.

NGUYỄN QUANG DONG, Kinh tế lượng, NXB Khoa học & Kỹ thuật, 2008.

A. KROGH and J. VEDELSBY, “Neural network ensembles, cross validation, and active learning”, in Advances in Neural Information Processing Systems,Vol. 7, The MIT Press, 1995, 231–238.

A. ZHOU and ET AL, “Multiobjective evolutionary algorithms: A survey of the state of the art,” Swarm and Evolutionary Computation, Vol. 1, No. 1, 2011, 32 – 49.

C. CHATFIELD, The Analysis of Time Series: an Introduction, 6th edition, Chapman & Hall/CRC, 2004.

C. SMITH and Y. JIN, “Evolutionary Multi-Objective Generation of Recurrent Neural Network Ensembles for Time Series Prediction”, Journal Neurocomputing, 2014, 302-311.

E. ALPAYDIN, Introduction to machine learning, 2nd edition, MIT Press, 2010.

G. BROWN and ET AL, “Diversity creationmethods: A survey and categorisation”, Journal of Information Fusion, Vol 6, 2004, 5-20.

G. VALENTINI, T. DIETTERICH, “Bias-variance analysis and ensembles of svm”, 3rd International Workshop on Multiple Classifier Systems, Springer-Verlag Berlin Heidelberg, Vol. 2364, 2002, 222–231.

HOZAIRI and ET AL, “Inplementation of nondomanated sorting genetic algorithm-II (NSGA-II) for Multiobjective Optimization Problem on distribution of Indonesian Navy Warship”, Journal of Theoretical and Applied Information Technology, Vol 6, No1, 2014, 274-281.

K. DEB and ET AL, “A Fast Elitist Multi-objective Genetic Algorithm: NSGA-II”, IEEE Transactions on Evolutionary Computation, 2002, 182 – 197.

K. DEB, “Multi-Objective Optimization Using Evolutionary Algorithms: An Introduction”, Springer London, 2001, 3-34.

K. GEBHARD and ET AL, Introduction to Modern Time Series Analysis, 2nd editor, Springer-verlag, 2013.

L. BREIMAN, “Bagging predictors”, Journal of Machine Learning, Vol. 24, No. 2, 1996, 123–140.

L. HANSEN, P. SALAMON, “Neural Network Ensembles”, IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 12, No. 10, 1990, 993– 1001.

M. PERRONE, L. COOPER, “When Networks Disagree: Ensemble Methods for Hybrid Neural Networks”, Artificial Neural Networks for Speech and Vision, Chapman & Hall, 1993, 126–142.

M. ŠTĚPNIČKA and ET AL, “Forecasting seasonal time series with computationalintelligence: contribution of a combination of distinct methods”, Proceedings of Conference on Eusflat-Lfa, Atlantis Press, 2011, 461-471.

P. ADHVARYU, M. PANCHAL, “A Review on Diverse Ensemble Methods for Classification”, IOSR Journal of Computer Engineering, Vol 1, No. 4, 2012, 27-32.

S. CHIAM and ET AL, “Multiobjective Evolutionary Neural Networks for Time Series Forecasting”, Lecture Notes in Computer Science, Vol 4403, Springer-Verlag Berlin Heidelberg, 2007, 346-360.

S. GU and Y. JIN, “Generating Diverse and Accurate ClassifierEnsembles Using Multi-Objective Optimization”, Proceedings of Conference on Computational Intelligence in Multi-Criteria Decision-Making, 2014.

U. NAFTALY and ET AL, “Optimal ensemble averaging of neural networks”, Network: Computation in Neural System, Vol. 8, No 3, 1997, 283–296.

Z. ZHOU, “Ensemble learning”, Berlin: Springer, 2009, 270-273.


Bài báo