RicciFlowRec: A Geometric Root Cause Recommender Using Ricci Curvature on Financial Graphs

2025-08-12

AI Summary

This paper addresses the weak interpretability and insufficient robustness of risk溯源 in dynamic financial graphs. Methodologically, it proposes a causal attribution framework grounded in discrete differential geometry—introducing Ricci curvature and Ricci flow into financial temporal graph modeling for the first time. The approach jointly leverages graph neural networks and FinBERT-based sentiment analysis to capture dynamic evolutionary relationships among stocks, macroeconomic indicators, and news. It quantifies local geometric stress and traces shock propagation paths to identify causal substructures. Key contributions include: (1) the first root-cause attribution model integrating geometric flow reasoning with financial semantics; (2) significantly enhanced robustness and interpretability in risk-aware ranking; and (3) empirical validation on S&P 500 data demonstrating stability against synthetic perturbations, with demonstrated applicability to downstream tasks such as portfolio optimization.

Technology Category

• Reasoning under Uncertainty: Causality
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We propose RicciFlowRec, a geometric recommendation framework that performs root cause attribution via Ricci curvature and flow on dynamic financial graphs. By modelling evolving interactions among stocks, macroeconomic indicators, and news, we quantify local stress using discrete Ricci curvature and trace shock propagation via Ricci flow. Curvature gradients reveal causal substructures, informing a structural risk-aware ranking function. Preliminary results on S&P~500 data with FinBERT-based sentiment show improved robustness and interpretability under synthetic perturbations. This ongoing work supports curvature-based attribution and early-stage risk-aware ranking, with plans for portfolio optimization and return forecasting. To our knowledge, RicciFlowRec is the first recommender to apply geometric flow-based reasoning in financial decision support.

Problem

• Performs root cause attribution in financial graphs
• Quantifies local stress using Ricci curvature
• Improves robustness in financial decision support

Innovation

• Uses Ricci curvature on financial graphs
• Traces shock propagation via Ricci flow
• Structural risk-aware ranking function