Open AccessShort-term Prediction of the CSI 300 Based on the BP Neural Network Model
Author(s) -
Shunyu Ning
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1437/1/012054
Subject(s) - artificial neural network , term (time) , index (typography) , statistics , econometrics , computer science , long term prediction , period (music) , mathematics , artificial intelligence , telecommunications , world wide web , acoustics , physics , quantum mechanics
In this paper, BP neural network is adopted to predict the Shanghai-Shenzhen 300 Index (CSI 300) during a short period of 60 days (beginning from March 7th, 2018), results of which are used to determine the prediction effect of the BP neural network model on CSI (China Securities Index) 300. In addition, the present study explores the prediction effect of the BP neural network during different time periods by grouping predicted results according to the length of time. It is found that the BP neural network model performs well in predicting the CSI 300. The prediction results reveal that the price would overall decline, the fluctuation frequency would be small, and the price fluctuations would be small. Comparison between the groups during different time periods shows that prediction during a time period of less than 20 days or more than 50 days incurs larger errors, the prediction during a time period of 30 to 40 days is more accurate, and predictions errors increase sharply during the time period of more than 50 days.