From News to Returns: A Granger-Causal Hypergraph Transformer on the Sphere
ArXiv ID: 2510.04357 “View on arXiv”
Authors: Anoushka Harit, Zhongtian Sun, Jongmin Yu
Abstract
We propose the Causal Sphere Hypergraph Transformer (CSHT), a novel architecture for interpretable financial time-series forecasting that unifies \emph{“Granger-causal hypergraph structure”}, \emph{“Riemannian geometry”}, and \emph{“causally masked Transformer attention”}. CSHT models the directional influence of financial news and sentiment on asset returns by extracting multivariate Granger-causal dependencies, which are encoded as directional hyperedges on the surface of a hypersphere. Attention is constrained via angular masks that preserve both temporal directionality and geometric consistency. Evaluated on S&P 500 data from 2018 to 2023, including the 2020 COVID-19 shock, CSHT consistently outperforms baselines across return prediction, regime classification, and top-asset ranking tasks. By enforcing predictive causal structure and embedding variables in a Riemannian manifold, CSHT delivers both \emph{“robust generalisation across market regimes”} and \emph{“transparent attribution pathways”} from macroeconomic events to stock-level responses. These results suggest that CSHT is a principled and practical solution for trustworthy financial forecasting under uncertainty.
Keywords: Granger Causality, Hypergraph Transformer, Riemannian Geometry, Time-Series Forecasting, Financial News, Equities
Complexity vs Empirical Score
- Math Complexity: 8.5/10
- Empirical Rigor: 7.0/10
- Quadrant: Holy Grail
- Why: The paper employs advanced mathematical concepts including Riemannian geometry, hypergraph theory, and causal inference with rigorous formulation, while also presenting empirical backtests on S&P 500 data across multiple tasks and market regimes.
flowchart TD
A["Research Goal: Forecast Asset Returns using Financial News & Sentiment"] --> B["Input Data: S&P 500 Returns & News (2018-2023)"]
B --> C["Methodology: Causal Sphere Hypergraph Transformer<br/>- Granger-Causal Hypergraph Extraction<br/>- Riemannian Geometry Embedding<br/>- Causally Masked Transformer"]
C --> D["Computation: Training on Market Regimes incl. COVID-19 Shock"]
D --> E["Outcomes:<br/>- Superior Return Prediction & Regime Classification<br/>- Robust Generalization<br/>- Interpretable Causal Attribution"]