Research Article
The Research of Stock Index Futures Price Forecasting Using DFA-LSTM Model Based on Panic Index
@INPROCEEDINGS{10.4108/eai.19-5-2023.2334279, author={Shuo Bian}, title={The Research of Stock Index Futures Price Forecasting Using DFA-LSTM Model Based on Panic Index}, proceedings={Proceedings of the 2nd International Conference on Bigdata Blockchain and Economy Management, ICBBEM 2023, May 19--21, 2023, Hangzhou, China}, publisher={EAI}, proceedings_a={ICBBEM}, year={2023}, month={7}, keywords={stock index futures; fractal market; the vix index; lstm neural network}, doi={10.4108/eai.19-5-2023.2334279} }- Shuo Bian
Year: 2023
The Research of Stock Index Futures Price Forecasting Using DFA-LSTM Model Based on Panic Index
ICBBEM
EAI
DOI: 10.4108/eai.19-5-2023.2334279
Abstract
With the rapid development of artificial intelligence, it is possible to use machine learning models to predict financial market prices more accurately. Based on the analysis of the efficiency and fractal characteristics of the Chinese stock index futures market, combined with the "panic index", this paper established an LSTM neural network model to predict the price of the CSI 300 stock index futures. The results show that: (1) Stock index futures market has long memory, and the strength of memory has time-varying characteristics; (2) Combining LSTM neural network with fractal method and panic index, the prediction accuracy is greatly improved; (3) Compared with the GARCH (1,1) model, the model constructed in this paper has better prediction effect.