COMPARING THE PREDICTION ACCURACY OF LSTM AND ARIMA MODELS FOR TIME-SERIES WITH PERMANENT FLUCTUATION

  • Ghahreman Abdoli Professor at University of Tehran, Faculty of Economics
  • Mohsen MehrAra Professor at University of Tehran, Faculty of Economics
  • Mohammad Ebrahim Ardalani Ph.D. Candidate at University of Tehran at Alborz campus
Palavras-chave: Prediction Model, LSTM, ARIMA, Forecast Accuracy, Tehran Stock Exchange

Resumo

In developing countries with an unstable economic system, permanent fluctuation in historical data is always a concern. Recognizing dependency and independency of variables are vague and proceeding a reliable forecast model is more complex than other countries. Although linearization of nonlinear multivariate economic time-series to predict, may give a result, the nature of data which shows irregularities in the economic system, should be ignored. New approaches of artificial neural network (ANN) help to make a prediction model with keeping data attributes. In this paper, we used the Tehran Stock Exchange (TSE) intraday data in 10 years to forecast the next 2 months. Long Short-Term Memory (LSTM) from ANN chooses and outputs compared with the autoregressive integrated moving average (ARIMA) model. The results show, although, in long term prediction, the forecast accuracy of both models reduce, LSTM outperforms ARIMA, in terms of error of accuracy, significantly.

Referências

Mukherjee, C. and White, H. and Wuyts, M. (2013). Econometrics and data analysis for developing countries: Routledge.

Ariyo, A. A. and Adewumi, A. O. and Ayo, C. K. (2014). Stock price prediction using the ARIMA model. Paper presented at the 2014 UKSim-AMSS 16th International Conference on Computer Modelling and Simulation.

Lin, C.-T. and Yeh, H.-Y. (2009). Empirical of the Taiwan stock index option price forecasting model–applied artificial neural network. Applied Economics, 41(15), 1965-1972.

Binner*, J. M. and Bissoondeeal, R. K. and Elger, T. and Gazely, A. M. and Mullineux, A. W. (2005). A comparison of linear forecasting models and neural networks: an application to Euro inflation and Euro Divisia. Applied Economics, 37(6), 665-680.

Wang, C.-C. and Hsu, Y.-S. and Liou, C.-H. (2011). A comparison of ARIMA forecasting and heuristic modelling. Applied Financial Economics, 21(15), 1095-1102.

Hansen, J. V. and Nelson, R. D. (2003). Time-series analysis with neural networks and ARIMA-neural network hybrids. Journal of Experimental & Theoretical Artificial Intelligence, 15(3), 315-330.

Long, W. and Lu, Z. and Cui, L. (2019). Deep learning-based feature engineering for stock price movement prediction. Knowledge-Based Systems, 164, 163-173.

Cao, J. and Li, Z. and Li, J. (2019). Financial time series forecasting model based on CEEMDAN and LSTM. Physica A: Statistical Mechanics and its Applications, 519, 127-139.

Zhang, K. and Zhong, G. and Dong, J. and Wang, S. and Wang, Y. (2019). Stock Market Prediction Based on Generative Adversarial Network. Procedia Computer Science, 147, 400-406.

Kim, T. and Kim, H. Y. (2019). Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data. PloS one, 14(2), e0212320.

Eapen, J. and Bein, D. and Verma, A. (2019). Novel Deep Learning Model with CNN and Bi-Directional LSTM for Improved Stock Market Index Prediction. Paper presented at the 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC).

Zhou, X. and Pan, Z. and Hu, G. and Tang, S. and Zhao, C. (2018). Stock market prediction on high-frequency data using generative adversarial nets. Mathematical Problems in Engineering, 2018.

Wang, H. and Guo, Z. and Chen, L. (2019). Financial Forecasting based on LSTM and Text Emotional Features. Paper presented at the 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC).

Yu, S.-S. and Chu, S.-W. and Chan, Y.-K. and Wang, C.-M. (2019). Share Price Trend Prediction Using CRNN with LSTM Structure. Smart Science, 1-9.

Sang, C. and Di Pierro, M. (2019). Improving trading technical analysis with TensorFlow Long Short-Term Memory (LSTM) Neural Network. The Journal of Finance and Data Science, 5(1), 1-11.

Kim, D. and Baek, C. (2019). Factor-augmented HAR model improves realized volatility forecasting. Applied Economics Letters, 1-8.

Chen, S. and Ge, L. (2019). Exploring the attention mechanism in LSTM-based Hong Kong stock price movement prediction. Quantitative Finance, 19(9), 1507-1515.

Borovkova, S. and Tsiamas, I. (2019). An ensemble of LSTM neural networks for high‐frequency stock market classification. Journal of Forecasting. Retrieved from https://onlinelibrary.wiley.com/doi/full/10.1002/for.2585

Liang, X. and Ge, Z. and Sun, L. and He, M. and Chen, H. (2019). LSTM with Wavelet Transform Based Data Preprocessing for Stock Price Prediction. Mathematical Problems in Engineering, 2019. Retrieved from http://downloads.hindawi.com/journals/mpe/2019/1340174.pdf

Du, J. and Liu, Q. and Chen, K. and Wang, J. (2019). Forecasting stock prices in two ways based on LSTM neural network. Paper presented at the 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC).

Karmiani, D. and Kazi, R. and Nambisan, A. and Shah, A. and Kamble, V. (2019). Comparison of Predictive Algorithms: Backpropagation, SVM, LSTM and Kalman Filter for Stock Market. Paper presented at the 2019 Amity International Conference on Artificial Intelligence (AICAI).

Pawar, K. and Jalem, R. S. and Tiwari, V. (2019). Stock Market Price Prediction Using LSTM RNN. In Emerging Trends in Expert Applications and Security (pp. 493-503): Springer.

Hiew, J. Z. G. and Huang, X. and Mou, H. and Li, D. and Wu, Q. and Xu, Y. (2019). BERT-based Financial Sentiment Index and LSTM-based Stock Return Predictability. arXiv preprint arXiv:1906.09024. Retrieved from https://arxiv.org/pdf/1906.09024.pdf

Hushani, P. (2019). Using Autoregressive Modelling and Machine Learning for Stock Market Prediction and Trading. Paper presented at the Third International Congress on Information and Communication Technology.

Manurung, A. H. and Budiharto, W. and Prabowo, H. (2018). ALGORITHM AND MODELING OF STOCK PRICES FORECASTING BASED ON LONG SHORT-TERM MEMORY (LSTM). ICIC Express Letters, 12, 1277–1283. Retrieved from http://icicelb.org/ell/contents/2018/12/el-12-12-11.pdf

Karakoyun, E. and Cibikdiken, A. (2018). Comparison of ARIMA Time Series Model and LSTM Deep Learning Algorithm for Bitcoin Price Forecasting. Paper presented at the The 13th Multidisciplinary Academic Conference in Prague 2018 (The 13th MAC 2018).

McNally, S. and Roche, J. and Caton, S. (2018). Predicting the price of Bitcoin using Machine Learning. Paper presented at the 2018 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP).

Rebane, J. and Karlsson, I. and Denic, S. and Papapetrou, P. (2018). Seq2Seq RNNs and ARIMA models for cryptocurrency prediction: A comparative study. SIGKDD Fintech, 18. Retrieved from https://pdfs.semanticscholar.org/c1ec/480f005244a2cfb93f1d3ad15c2d22b864d6.pdf

Huynh, H. D. and Dang, L. M. and Duong, D. (2017). A new model for stock price movements prediction using deep neural network. Paper presented at the Proceedings of the Eighth International Symposium on Information and Communication Technology.

Selvin, S. and Vinayakumar, R. and Gopalakrishnan, E. and Menon, V. K. and Soman, K. (2017). Stock price prediction using LSTM, RNN and CNN-sliding window model. Paper presented at the 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

Li, H. and Shen, Y. and Zhu, Y. (2018). Stock Price Prediction Using Attention-based Multi-Input LSTM. Paper presented at the Asian Conference on Machine Learning.

Yu, S. and Li, Z. (2018). Forecasting stock price index volatility with LSTM deep neural network. In Recent Developments in Data Science and Business Analytics (pp. 265-272): Springer.

Skehin, T. and Crane, M. and Bezbradica, M. (2018). Day ahead forecasting of FAANG stocks using ARIMA, LSTM networks and wavelets.

Kim, H. Y. and Won, C. H. (2018). Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models. Expert Systems with Applications, 103, 25-37.

Hiransha, M. and Gopalakrishnan, E. A. and Menon, V. K. and Soman, K. (2018). NSE stock market prediction using deep-learning models. Procedia Computer Science, 132, 1351-1362.

Nagahisarchoghaei, Mohammad and Nagahi, Morteza and Soleimani, Nadia, Impact of Exchange Rate Movements on Indian Firm Performance (2018). International Journal of Finance and Accounting, Vol. 7 No. 4, 2018, pp. 108-121. doi: 10.5923/j.ijfa.20180704.03..

Nagahi, Morteza and Nagahisarchoghaei, Mohammad and Soleimani, Nadia and Jaradat, Raed M., Hedge Strategies of Corporate Houses (February 7, 2018). Journal of Business Administration Research, 7(1), 6..

Baughman, M. and Haas, C. and Wolski, R. and Foster, I. and Chard, K. (2018). Predicting Amazon spot prices with LSTM networks. Paper presented at the Proceedings of the 9th Workshop on Scientific Cloud Computing.

Shah, D. and Campbell, W. and Zulkernine, F. H. (2018). A Comparative Study of LSTM and DNN for Stock Market Forecasting. Paper presented at the 2018 IEEE International Conference on Big Data (Big Data).

Minami, S. (2018). Predicting Equity Price with Corporate Action Events Using LSTM-RNN. Journal of Mathematical Finance, 8(1), 58-63.

Naik, N. and Mohan, B. R. (2019). Study of Stock Return Predictions Using Recurrent Neural Networks with LSTM. Paper presented at the International Conference on Engineering Applications of Neural Networks.

Pai, P.-F. and Lin, C.-S. (2005). A hybrid ARIMA and support vector machines model in stock price forecasting. Omega, 33(6), 497-505.

Nandakumar, R. and R, U. K. and R, V. and Lokeswari, Y. V. (2018). Stock Price Prediction Using Long Short Term Memory. International Research Journal of Engineering and Technology, 05(03). Retrieved from https://www.irjet.net/archives/V5/i3/IRJET-V5I3788.pdf

Fischer, T. and Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654-669.

Shao, X. and Ma, D. and Liu, Y. and Yin, Q. (2017). Short-term forecast of stock price of multi-branch LSTM based on K-means. Paper presented at the 2017 4th International Conference on Systems and Informatics (ICSAI).

Li, J. and Bu, H. and Wu, J. (2017). Sentiment-aware stock market prediction: A deep learning method. Paper presented at the 2017 International Conference on Service Systems and Service Management.

Zhuge, Q. and Xu, L. and Zhang, G. (2017). LSTM Neural Network with Emotional Analysis for Prediction of Stock Price. Engineering Letters, 25(2). Retrieved from https://pdfs.semanticscholar.org/1a08/bcc2e0866e64d7b4d8d7a4c670faa26ab13d.pdf
Bao, W. and Yue, J. and Rao, Y. (2017). A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PloS one, 12(7), e0180944.

Choi, H. K. (2018). Stock price correlation coefficient prediction with ARIMA-LSTM hybrid model. arXiv preprint arXiv:1808.01560. Retrieved from https://arxiv.org/pdf/1808.01560.pdf

Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175.

Pang, X. and Zhou, Y. and Wang, P. and Lin, W. and Chang, V. (2018). An innovative neural network approach for stock market prediction. The Journal of Supercomputing, 1-21.

Pang, X. W. and Zhou, Y. and Wang, P. and Lin, W. and Chang, V. (2018). Stock Market Prediction based on Deep Long Short Term Memory Neural Network. Paper presented at the COMPLEXIS.

Di Persio, L. and Honchar, O. (2017). Recurrent neural networks approach to the financial forecast of Google assets. International journal of Mathematics and Computers in simulation, 11.

Olah, C. (2015). Understanding lstm networks. Retrieved from https://colah.github.io/posts/2015-08-Understanding-LSTMs/

DAVODI, H., SHABANALI, F. H., & KALANTARI, K. (2012). An investigation of technology development barriers in Agricultural Science and Technology Parks of Tehran University.

Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.

Davodi, H., Iravani, H., Fami, H. S., & Ameri, Z. D. (2017). Affecting Factors on Water Resources' Sustainability in case of small holding farmers, Alborz province, Islamic Republic of Iran. Advances in Bioresearch, 8(3).

Box, G. E. and Jenkins, G. M. and Reinsel, G. (1970). Time series analysis: forecasting and control Holden-day San Francisco. BoxTime Series Analysis: Forecasting and Control Holden Day1970.

Rashid, T. A. and Fattah, P. and Awla, D. K. (2018). Using Accuracy Measure for Improving the Training of LSTM with Metaheuristic Algorithms. Procedia Computer Science, 140, 324-333.

Kingma, D. P. and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.

Siami-Namini, S. and Namin, A. S. (2018). Forecasting economics and financial time series: Arima vs. lstm. arXiv preprint arXiv:1803.06386. Retrieved from https://arxiv.org/ftp/arxiv/papers/1803/1803.06386.pdf
Publicado
2020-02-24
Como Citar
ABDOLI, G.; MEHRARA , M.; EBRAHIM ARDALANI, M. COMPARING THE PREDICTION ACCURACY OF LSTM AND ARIMA MODELS FOR TIME-SERIES WITH PERMANENT FLUCTUATION . Gênero & Direito, v. 9, n. 2, 24 fev. 2020.
Seção
Seção Livre