Quantifying neural network uncertainty under volatility clustering
By Steven Y. K. Wong, Jennifer S. K. Chan, Lamiae Azizi
Rating
1455
Battle Count: 36
Relevance
9/10
Highly relevant for improving uncertainty estimates in financial forecasting, which is crucial for risk management and portfolio optimization in quantitative trading
Implementation Complexity
7/10
Requires understanding of advanced neural network architectures and ensemble methods, but builds on existing frameworks
Reproducibility
4/5
Detailed methodology and architecture provided, experiments on public datasets
About this paper
Methodology: Combined Method. Problem types: Time Series Forecasting, Uncertainty Quantification, Regression.
The interactive Everscope explorer (charts, battles, favorites) loads below.