The stock market is characterized by the coexistence of high risks. In order to seek benefits and avoid risks, people do not hesitate to explore its laws and seek the best forecasting methods and methods. The purpose of this paper is to study the stock trend prediction method and optimization based on neural network. The predictability of the securities market is expounded. On the basis of the prediction model based on the historical stock transaction data, a stock prediction model integrating news and investor sentiment is constructed. The advantage of linear and complex time series forecasting problems, the stock training data is used as the input data of the improved CLSTM and BiLSTM deep neural network, and the stock trend forecasting model is trained. Continuously optimize and improve the model, select appropriate parameters to obtain a good stock trend prediction model. By continuously revising the LSTM level, the accuracy of the stock trend prediction model is significantly improved.

Yuan Fang. Prediction Method and Optimization of Stock Trend Based on Neural Network. International Journal of Neural Network (2021), Vol. 2, Issue 4: 9-16. https://doi.org/10.38007/NN.2021.020402.

[1] Ziarnetzky T, Mnch L, Uzsoy R. Simulation-Based Performance Assessment of Production Planning Models With Safety Stock and Forecast Evolution in Semiconductor Wafer Fabrication. IEEE Transactions on Semiconductor Manufacturing, 2020, 33(1):1-12. https://doi.org/10.1109/TSM.2019.2958526

[2] Thanh D V, Hai N M, Hieu D D. Building Unconditional Forecast Model of Stock Market Indexes using Combined Leading Indicators and Principal Components: Application to Vietnamese Stock Market. Indian Journal of Science & Technology, 2018, 11(2):1-13. https://doi.org/10.17485/ijst/2018/v11i2/104908

[3] Thapa P, Aryal B. Use of geometric Brownian motion to forecast stock market scenario using post covid-19 NEPSE index. BIBECHANA, 2021, 18(2):50-60. https://doi.org/10.3126/bibechana.v18i2.31180

[4] Fan R, Taylor S J, Sandri M. Density forecast comparisons for stock prices, obtained from high‐frequency returns and daily option prices. Journal of Futures Markets, 2018, 38(1):83-103. https://doi.org/10.1002/fut.21859

[5] Nnachi O I. Improving the Forecast Accuracy of Oil-Stock Nexus in GCC Countries. Theoretical Economics Letters, 2018, 08(14):3073-3091. https://doi.org/10.4236/tel.2018.814191

[6] Uysal F, Erturan B. Volatility forecast with artificial neural networks as univariate time series, with examples from stock market indexes. Global Journal of Business Economics and Management Current Issues, 2018, 7(3):291-299. https://doi.org/10.18844/gjbem.v7i3.2965

[7] Alfonso G, Carnerero A D, Ramirez D R, et al. Stock Forecasting Using Local Data. IEEE Access, 2020, PP(99):1-1.

[8] Salisu A A, Swaray R, Oloko T F. Improving the predictability of the oil–US stock nexus: The role of macroeconomic variables. Economic Modelling, 2019, 76(JAN.):153-171. https://doi.org/10.1016/j.econmod.2018.07.029

[9] Mcmillan D G. Stock return predictability: Using the cyclical component of the price ratio. Research in International Business and Finance, 2019, 48(APR.):228-242. https://doi.org/10.1016/j.ribaf.2018.12.014

[10] Arjun R, Suprabha K R. Forecasting banking sectors in Indian stock markets using machine intelligence. International Journal of Hybrid Intelligent Systems, 2019, 15(3):129-142. https://doi.org/10.3233/HIS-190266

[11] Albahli S, Awan A, Nazir T, et al. A deep learning method DCWR with HANet for stock market prediction using news articles. Complex & Intelligent Systems, 2022, 8(3):2471-2487. https://doi.org/10.1007/s40747-022-00658-0

[12] Jan M N, Ayub U. DO THE FAMA AND FRENCH FIVE-FACTOR MODEL FORECAST WELL USING ANN? Journal of Business Economics and Management, 2019, 20(1):168-191. https://doi.org/10.3846/jbem.2019.8250

[13] Joseph D , Roger A D, Harshdeep A, et al. Improving U.S. Stock Return Forecasts: A 'Fair-Value' Cape Approach. Social Science Electronic Publishing, 2018, 44(3):43-55. https://doi.org/10.3905/jpm.2018.44.3.043

[14] Kim H Y, Won C H. Forecasting the Volatility of Stock Price Index: A Hybrid Model Integrating LSTM with Multiple GARCH-Type Models. Expert Systems with Applications, 2018, 103(aug.):25-37. https://doi.org/10.1016/j.eswa.2018.03.002

[15] Pashaei Z, Dehkharghani R. Stock Market Modeling Using Artificial Neural Network and Comparison with Classical Linear Models. Signal and Data Processing, 2021, 17(4):89-102. https://doi.org/10.29252/jsdp.17.4.89

[16] Kumari A B, Sahoo P K. A Novel Model to Predict Stock Market Price. High Technology Letters, 2021, 26(12):768-777.

[17] Efat M, Azad R U, Ahammed K. A Predictive Meta Model for Forecasting Stock Price using Time Series Data. International Journal of Advanced Trends in Computer Science and Engineering, 2021, 10(1):345-356. https://doi.org/10.30534/ijatcse/2021/501012021

[18] Zandi G, Torabi R, Mohammad M A, et al. Research on Stock Portfolio Based on Time Series Prediction and Multi-Objective Optimization. Advances in Mathematics Scientific Journal, 2021, 10(3):1509–1528. https://doi.org/10.37418/amsj.10.3.37