The Role of Neural Network based on Multi Feature Input in Stock Market Valuation and Prediction: A Case Study of LSTM

Lei Peng

《Frontiers in Economics and Management》 2卷9期 (2021/09) Pp. 173-180

https://doi.org/10.6981/FEM.202109_2(9).0023

摘要

In the past, neural network has become a popular tool in stock market research, especially in forecasting. As one of the classic models of deep learning technology, long-term memory (LSTM) neural network has a great advantage in mining long-term dependence of sequential data. In order to explore the role of neural network in the stock market, this paper uses AutoML technology to build a suitable neural network model based on LSTM, combines the data of financial statements, macroeconomic indicators and stock technical indicators into different feature combinations and applies them to five stocks in different industries of NASDAQ, which provides a reference for the selection of feature values for the future prediction of stock prices. In this paper, neural network is applied to the stock value prediction, which provides a new idea for the construction of an effective market.

關鍵字

LSTM ； Stock Price Forecast ； Valuation ； Market Effectiveness

參考文獻

Chang S V, Gan K S, On C K, et al. A review of stock market prediction with Artificial neural network (ANN). IEEE International Conference on Control System, Computing and Engineering. IEEE, 2014:477-482

Yaqub M U, Al-Ahmadi M S. Application of Combined Arma-Neural Network Models to Predict Stock Prices. The Multidisciplinary International Social Networks Conference on Socialinformatics 2016,Data Science. ACM, 2016:40.

Jabin S. Stock Market Prediction using Feed-forward Artificial Neural Network. International Journal of Computer Applications, 2014,99(9):4-8.

Picasso, A., Merello, S., Ma, Y., Oneto, L., & Cambria, E. (2019). Technical analysis and sentiment embeddings for market trend prediction. Expert Systems with Applications, 135, 60–70. https:// doi.org/10.1016/j.eswa.2019.06.014

Gers F A, Schmidhuber J, Cummins F. Learning to forget: continual prediction with LSTM. Neural Computation, 2000, 12(10):2451.