Research And Analysis of Neural Networks for Financial Time Series Prediction

Read full text Summarise with VIRAT
Authors: Feiyi FENG
Cited by: 0
References: 5

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Financial time series prediction is crucial for portfolio optimization, risk management, and financial policy-making. However, traditional technical analysis and statistical models, limited by linear assumptions and data distribution, struggle to handle the market’s nonlinear, high-volatility traits. Neural networks, with their nonlinear mapping and autonomous learning, offer a key solution. This paper reviews the field’s research over the past five years, focusing on four mainstream technologies: Recurrent Neural Network, functional denoising autoencoder, Long Short-Term Memory Neural Network, and hypergraph neural networks. It analyzes each model’s principles, features, pros and cons, and verifies their effectiveness using indicators like IC, Sharpe Ratio, and RMSE on datasets from A-shares, U.S. stocks, and cryptocurrencies. Models integrating spatiotemporal features (e.g., hypergraph neural networks) perform exceptionally well. The paper also notes current challenges, such as single data usage and weak cross-market generalization. Future optimization should involve multi-source data fusion and cross-market transfer learning, providing references for financial practice and advancing neural networks’ practical application.

Fields of Study & Subjects

Stock Market Forecasting Methods Time Series Analysis and Forecasting Financial Markets and Investment Strategies

Publication details

Journal / source
Frontiers in Computing and Intelligent Systems
Volume
16
Issue
1
Pages
69–77
Publication date
27 March 2026
Language
EN