From GARCH to Neural Network for Volatility Forecast
By Pengfei Zhao, Haoren Zhu, Wilfred Siu Hung NG, Dik Lun Lee
Rating
1320
Battle Count: 84
Relevance
9/10
Highly relevant for improving volatility forecasting in quantitative trading strategies, risk management, and portfolio optimization
Implementation Complexity
7/10
Requires understanding of both GARCH models and neural networks, as well as implementation of custom neural network architectures
Reproducibility
4/5
The paper provides detailed methodology and experimental setup, facilitating reproducibility. Code availability would improve the score.
About this paper
Methodology: GARCH-NN. Problem types: Time Series Forecasting, Volatility Prediction.
The interactive Everscope explorer (charts, battles, favorites) loads below.