RAGIC: Risk-Aware Generative Adversarial Model for Stock Interval Construction
By Jingyi Gu, Wenlu Du, Guiling (Grace) Wang
Rating
1379
Battle Count: 53
Relevance
9/10
RAGIC provides valuable interval predictions for stock indices, which can be directly applied to various quantitative trading strategies, risk management, and decision-making processes
Implementation Complexity
7/10
The model involves complex components like GAN and custom modules, but relies on publicly available data and common deep learning frameworks
Reproducibility
4/5
The paper provides detailed methodology and algorithm descriptions, but lacks specific hyperparameter settings for full reproducibility
About this paper
Methodology: RAGIC. Problem types: Time Series Forecasting, Interval Prediction, Risk Management.
The interactive Everscope explorer (charts, battles, favorites) loads below.