DiffsFormer: A Diffusion Transformer on Stock Factor Augmentation
By Yuan Gao, Haokun Chen, Xiang Wang, Zhicai Wang, Xue Wang, Jinyang Gao, Bolin Ding
Rating
1393
Battle Count: 31
Relevance
9/10
The paper presents a novel approach to enhance stock forecasting models, which is highly relevant to quantitative trading strategies.
Implementation Complexity
7/10
Implementing diffusion models and the proposed transfer learning framework requires significant expertise in deep learning and financial data processing.
Reproducibility
4/5
The paper provides detailed algorithms, hyperparameters, and experimental setup. Code is not explicitly mentioned as available.
About this paper
Methodology: DiffsFormer. Problem types: Time Series Forecasting, Regression.
The interactive Everscope explorer (charts, battles, favorites) loads below.