In order to verify that the model optimized by the mayfly algorithm improves the prediction ability of the stock index, this paper will compare and analyse the prediction results of a single algorithm model as the benchmark model and the model after the optimization of the mayfly algorithm. Therefore, this paper will show the comparative analysis of the prediction results of the optimization algorithm model based on the mayfly algorithm. This paper employs mayfly algorithm (MA), which is a newly developed algorithm recently, to optimize the algorithm models back propagation (BP), extreme learning machine (ELM), and kernel-based extreme learning (KELM) and the long-short term memory (LSTM) model for parameter optimization respectively. These algorithm after optimized would be show that is MA-BPNN model, MA-KELM model, MA-KELM model and MA-LSTM model respectively. From comparative analysis shows that the BPNN model is the better forecasting effect of a single algorithm model, and the model ELM optimized by the mayfly algorithm shows better forecasting ability. Additionally, the prediction ability of LSTM model is better without optimization, compared with itself after optimized by mayfly algorithm. We found that the model after algorithm optimization will basically greatly improve its prediction ability, and the specific performance is that its prediction error will be reduced.

Yi Chen, Eva Khong. Time Series Forecasting Model Based on Mayfly Algorithm Optimization. Academic Journal of Business & Management (2022) Vol. 4, Issue 10: 94-99. https://doi.org/10.25236/AJBM.2022.041016.

[1] Lin, Y., Yan, Y., Xu, J., Liao, Y., & Ma, F. (2021). Forecasting stock index price using the CEEMDAN-LSTM model. The North American Journal of Economics And Finance, 57, 101421. https://doi.org/ 10.1016/j.najef. 2021.101421

[2] Lin, H., Sun, Q., & Chen, S. (2020). Reducing Exchange Rate Risks in International Trade: A Hybrid Forecasting Approach of CEEMDAN and Multilayer LSTM. Sustainability, 12(6), 2451. https://doi.org/ 10.3390/su12062451

[3] Fan, J., & Yao, Q. (2008). Nonlinear time series: nonparametric and parametric methods. Springer Science & Business Media.

[4] Lin, H., & Sun, Q. (2020). Crude Oil Prices Forecasting: An Approach of Using CEEMDAN-Based Multi-Layer Gated Recurrent Unit Networks. Energies, 13(7), 1543. https: //doi.org/ 10.3390/ en13071543

[5] Chen, L., Chi, Y., Guan, Y., & Fan, J. (2019, May). A hybrid attention-based EMD-LSTM model for financial time series prediction. In 2019 2nd International Conference on Artificial Intelligence and Big Data (ICAIBD) (pp. 113-118). IEEE.

[6] Riesgo García, M., Krzemień, A., Manzanedo del Campo, M., Escanciano García-Miranda, C., & Sánchez Lasheras, F. (2018). Rare earth elements price forecasting by means of transgenic time series developed with ARIMA models. Resources Policy, 59, 95-102. https://doi.org/10.1016/ j.resourpol. 2018.06.003

[7] Zhang, G., Eddy Patuwo, B., & Y. Hu, M. (1998). Forecasting with artificial neural networks:. International Journal of Forecasting, 14(1), 35-62. https://doi.org/10.1016/s0169-2070(97) 00044-7

[8] Lv, P., Wu, Q., Xu, J., & Shu, Y. (2022). Stock Index Prediction Based on Time Series Decomposition and Hybrid Model. Entropy, 24(2), 146. https://doi.org/10.3390/e24020146

[9] Sezer, O., Gudelek, M., & Ozbayoglu, A. (2020). Financial time series forecasting with deep learning : A systematic literature review: 2005–2019. Applied Soft Computing, 90, 106181. https://doi.org/10. 1016/j.asoc.2020.106181

[10] Siami-Namini, S., Tavakoli, N., & Namin, A. S. (2018, December). A comparison of ARIMA and LSTM in forecasting time series. In 2018 17th IEEE international conference on machine learning and applications (ICMLA) (pp. 1394-1401). IEEE.

[11] Karmiani, D., Kazi, R., Nambisan, A., Shah, A., & Kamble, V. (2019, February). Comparison of predictive algorithms: backpropagation, SVM, LSTM and Kalman Filter for stock market. In 2019 Amity International Conference on Artificial Intelligence (AICAI) (pp. 228-234). IEEE.

[12] Makala, D., & Li, Z. (2021). Prediction of gold price with ARIMA and SVM. Journal Of Physics: Conference Series, 1767(1), 012022. https://doi.org/10.1088/1742-6596/1767/1/012022

[13] Kumar, M., & Thenmozhi, M. (2014). Forecasting stock index returns using ARIMA-SVM, ARIMA-ANN, and ARIMA-random forest hybrid models. International Journal of Banking, Accounting And Finance, 5(3), 284. https://doi.org/10.1504/ijbaaf.2014.064307

[14] Büyükşahin, Ü., & Ertekin, Ş. (2019). Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode decomposition. Neurocomputing, 361, 151-163. https://doi.org/10.1016/j.neucom.2019.05.099

[15] Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654-669. https://doi.org /10.1016/j.ejor.2017.11.054

[16] Ding, G., & Qin, L. (2019). Study on the prediction of stock price based on the associated network model of LSTM. International Journal of Machine Learning And Cybernetics, 11(6), 1307-1317. https://doi.org/10.1007/s13042-019-01041-1

[17] Qin, J., Tao, Z., Huang, S., & Gupta, G. (2021, March). Stock price forecast based on ARIMA model and BP neural network model. In 2021 IEEE 2nd International Conference on Big Data,

[18] Rumelhart, D., Hinton, G., & Williams, R. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533-536. https://doi.org/10.1038/323533a0

[19] Wu, D., Wang, X., & Wu, S. (2021). A Hybrid Method Based on Extreme Learning Machine and Wavelet Transform Denoising for Stock Prediction. Entropy, 23(4), 440. https://doi.org/ 10.3390/ e23040440

[20] Wang, F., Zhang, Y., Rao, Q., Li, K., & Zhang, H. (2016). Exploring mutual information-based sentimental analysis with kernel-based extreme learning machine for stock prediction. Soft Computing, 21(12), 3193-3205. https://doi.org/10.1007/s00500-015-2003-z

[21] Das, S., & Padhy, S. (2015). A novel hybrid model using teaching–learning-based optimization and a support vector machine for commodity futures index forecasting. International Journal of Machine Learning And Cybernetics, 9(1), 97-111. https://doi.org/10.1007/s13042-015-0359-0

[22] Bao, W., Yue, J., & Rao, Y. (2017). A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PLOS ONE, 12(7), e0180944. https://doi.org/ 10.1371/journal.pone.0180944

[23] Büyükşahin, Ü., & Ertekin, Ş. (2019). Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode decomposition. Neurocomputing, 361, 151-163. https://doi.org/10.1016/j.neucom. 2019.05.099

[24] Liu, M., Ding, L., & Bai, Y. (2021). Application of hybrid model based on empirical mode decomposition, novel recurrent neural networks and the ARIMA to wind speed prediction. Energy Conversion And Management, 233, 113917. https://doi.org/10.1016/j.enconman. 2021.113917

[25] Zhou, F., Zhou, H., Yang, Z., & Yang, L. (2019). EMD2FNN: A strategy combining empirical mode decomposition and factorization machine based neural network for stock market trend prediction. Expert Systems With Applications, 115, 136-151. https://doi.org/10.1016/j.eswa.2018.07.065

[26] Huang, N., Shen, Z., Long, S., Wu, M., Shih, H., & Zheng, Q. et al. (1998). The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings Of The Royal Society Of London. Series A: Mathematical, Physical and Engineering Sciences, 454(1971), 903-995. https://doi.org/10.1098/rspa.1998.0193

[27] Zhou, Y., Li, T., Shi, J., & Qian, Z. (2019). A CEEMDAN and XGBOOST-Based Approach to Forecast Crude Oil Prices. Complexity, 2019, 1-15. https://doi.org/10.1155/2019/4392785

[28] Witaszek, J. (1995). Backpropagation: Theory, architectures, applications. Neurocomputing, 9(3), 358-359. https://doi.org/10.1016/0925-2312(95)90002-0

[29] Yang, Z., Ce, L., & Lian, L. (2017). Electricity price forecasting by a hybrid model, combining wavelet transform, ARMA and kernel-based extreme learning machine methods. Applied Energy, 190, 291-305. https://doi.org/10.1016/j.apenergy.2016.12.130

[30] Huang, G., Zhu, Q., & Siew, C. (2006). Extreme learning machine: Theory and applications. Neurocomputing, 70(1-3), 489-501. https://doi.org/10.1016/j.neucom.2005.12.126

[31] Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735

[32] Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems, 28(10), 2222-2232.

[33] Zervoudakis, K., & Tsafarakis, S. (2020). A mayfly optimization algorithm. Computers &Amp; Industrial Engineering, 145, 106559. https://doi.org/10.1016/j.cie.2020.106559