VN-INDEX TREND PREDICTION USING LONG-SHORT TERM MEMORY NEURAL NETWORKS

Nguyen Ngoc Tra; Ho Phuoc Tien; Nguyen Thanh Dat; Nguyen Ngoc Vu

doi:10.31130/ict-ud.2019.94

Nguyen Ngoc Tra The University of Danang, University of Economics, Vietnam
Ho Phuoc Tien The University of Danang, University of Science and Technology, Vietnam
Nguyen Thanh Dat The University of Danang, University of Economics, Vietnam
Nguyen Ngoc Vu The University of Danang, Vietnam

DOI: https://doi.org/10.31130/ict-ud.2019.94

Abstract

The paper attemps to forecast the future trend of Vietnam index (VN-index) by using long-short term memory (LSTM) networks. In particular, an LSTM-based neural network is employed to study the temporal dependence in time-series data of past and present VN index values. Empirical forecasting results show that LSTM-based stock trend prediction offers an accuracy of about 60% which outperforms moving-average-based prediction.

Downloads

Download data is not yet available.

References

[1] N. Kohzadi, M. S. Boyd, B. Kermanshahi, & I. Kaastra, “A comparison of artificial neural network and time series models for forecasting commodity prices”, Neurocomputing, 10(2), 1996, 169-181.
[2] I. Aizenberg, L. Sheremetov, L. Villa-Vargas & J. Martinez-Muñoz, “Multilayer neural network with multi-valued neurons in time series forecasting of oil production”, Neurocomputing, 175, 2016, 980-989.
[3] A. Sagheer & M. Kotb, “Time series forecasting of petroleum production using deep LSTM recurrent networks”, Neurocomputing, 323, 2019, 203-213.
[4] S. Pyo, J. Lee, M. Cha & H. Jang, “Predictability of machine learning techniques to forecast the trends of market index prices: Hypothesis testing for the Korean stock markets”, PLoS ONE 12(11), 2017.
[5] C.Y. Ma, M.H. Chen, Z. Kira & G.A. Regib, “TS-LSTM and temporal-inception: Exploiting spatiotemporal dynamics for activity recognition”, Signal Processing: Image Communication, 71, 2019, 76-87.
[6] Z. Guo, H. Wang, Q. Liu & J. Yang, “A Feature Fusion Based Forecasting Model for Financial Time Series”, PLoS ONE 9(6), 2014.
[7] H. Guan, Z. Dai, A. Zhao & J. He, “A novel stock forecasting model based on High-order-fuzzy-fluctuation Trends and Back Propagation Neural Network”, PLoS ONE 13(2), 2018.
[8] T. Kim & H. Y. Kim, “Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data”, PLoS ONE 14(2), 2019.
[9] B. Yang, W. Zhang & H. Wang, “Stock Market Forecasting Using Restricted Gene Expression Programming”, Computational Intelligence and Neuroscience, 7198962, 2019.
[10] S. Hochreiter & J. Schmidhuber, “Long short-term memory”, Neural Computation, 9 (8), 1997, 1735–1780.
[11] N. Liu & J. Han, “A Deep Spatial Contextual Long-Term Recurrent Convolutional Network for Saliency Detection”, IEEE Transactions on Image Processing, 27(7), 2018, 3264-3274.
[12] Y. Feng, L. Ma, W. Liu & J. Luo, “Spatio-temporal Video Re-localization by Warp LSTM”, IEEE Conference on Computer Vision and Pattern Recognition, 2019.
[13] Y. LeCun, Y. Bengio & G. Hinton, “Deep learning”, Nature, 521, 2015, 436–444.
[14] T. Ho-Phuoc, “CIFAR10 to Compare Visual Recognition Performance between Deep Neural Networks and Humans”, arXiv, 2018.
[15] S. An, Z. Ling & L. Dai, “Emotional statistical parametric speech synthesis using LSTM-RNNs”, Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2017.
[16] T. Young, D. Hazarika, S. Poria & E. Cambria, “Recent Trends in Deep Learning Based Natural Language Processing”, arXiv, 2017.
[17] C. Si, W. Chen, W. Wang, L. Wang & T. Tan, “An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition”, IEEE Conference on Computer Vision and Pattern Recognition, 2019.