Predictive Analysis of Treasury Bond Risk Based on Combinatorial Intelligence Algorithm

Bank bonds support infrastructure construction, stabilize effective demand, increase financing demand, activate the capital market, and promote the recovery of consumer confidence. This will undoubtedly be a win-win for accelerating economic recovery. In this paper, the particle swarm optimization a...

Full description

Saved in:
Bibliographic Details
Published in2024 IEEE 2nd International Conference on Sensors, Electronics and Computer Engineering (ICSECE) pp. 976 - 981
Main Authors Siran, Lian, Jianya, Zhao
Format Conference Proceeding
LanguageEnglish
Published IEEE 29.08.2024
Subjects
Economics
errors
Neural networks
Particle swarm optimization
Prediction algorithms
Predictive analytics
Sensors
Training
Treasury bonds
Online AccessGet full text

Cover

More Information
Summary:Bank bonds support infrastructure construction, stabilize effective demand, increase financing demand, activate the capital market, and promote the recovery of consumer confidence. This will undoubtedly be a win-win for accelerating economic recovery. In this paper, the particle swarm optimization algorithm and the BP neural network algorithm are used to predict the national debt, and the final fitness value the quality of particle swarm optimization. The average value of the predicted results is 6.37 trillion yuan, the mean of the absolute error of the prediction is 0.05, and the mean of the relative error is 0.013, and the forecast results meet the standard requirements.
DOI:10.1109/ICSECE61636.2024.10729550