Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction

Qianggang Ding, Haochen Shi, Luis Castejón Lozano, Miguel Conner, Juan Abia, Luis Gallego-Ledesma, Joshua Fellowes, Gerard Conangla Planes, Adam Elwood, Bang Liu

Abstract

We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction that unifies symbolic relational priors, dynamic graph exploration, and LLM-guided decision making in a single end-to-end pipeline. The approach performs rule-guided multi-hop exploration restricted to admissible relation sequences, grounds candidate reasoning chains in contemporaneous news, and aggregates fully grounded evidence into auditable \texttt{UP}/\texttt{DOWN} verdicts with human-readable paths connecting text and structure. On an S\&P~500 benchmark, the method achieves 55.1\% accuracy, 55.7\% precision, 71.5\% recall, and 60.8\% F1, surpassing strong baselines and improving recall and F1 over the best graph baseline under identical evaluation. The gains stem from (i) rule-guided exploration that focuses search on economically meaningful motifs rather than arbitrary walks, and (ii) text-grounded consolidation that selectively aggregates high-confidence, fully grounded hypotheses instead of uniformly pooling weak signals. Together, these choices yield higher sensitivity without sacrificing selectivity, delivering predictive lift with faithful, auditably interpretable explanations.

TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction

Abstract

We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction that unifies symbolic relational priors, dynamic graph exploration, and LLM-guided decision making in a single end-to-end pipeline. The approach performs rule-guided multi-hop exploration restricted to admissible relation sequences, grounds candidate reasoning chains in contemporaneous news, and aggregates fully grounded evidence into auditable \texttt{UP}/\texttt{DOWN} verdicts with human-readable paths connecting text and structure. On an S\&P~500 benchmark, the method achieves 55.1\% accuracy, 55.7\% precision, 71.5\% recall, and 60.8\% F1, surpassing strong baselines and improving recall and F1 over the best graph baseline under identical evaluation. The gains stem from (i) rule-guided exploration that focuses search on economically meaningful motifs rather than arbitrary walks, and (ii) text-grounded consolidation that selectively aggregates high-confidence, fully grounded hypotheses instead of uniformly pooling weak signals. Together, these choices yield higher sensitivity without sacrificing selectivity, delivering predictive lift with faithful, auditably interpretable explanations.
Paper Structure (69 sections, 20 equations, 5 figures, 3 tables, 1 algorithm)

This paper contains 69 sections, 20 equations, 5 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Problem Formulation
  5. Text sources and as-of constraint.
  6. Rules.
  7. Prediction task.
  8. Objective.
  9. Knowledge Graph Construction
  10. Entity types.
  11. Relations.
  12. Anchoring to text.
  13. Rule integration.
  14. Automated Rule Mining
  15. Rule definition.
  16. ...and 54 more sections

Figures (5)

  • Figure 1: Structure of the temporal financial knowledge graph showing entity types, relation categories, and temporal validity intervals.
  • Figure 2: Overview of our knowledge graph reasoning framework showing the integration of automated rule mining and temporal graph reasoning.
  • Figure 3: Example of interpretable reasoning paths showing how our knowledge graph reasoning framework connects stocks to textual evidence.
  • Figure 4: Cumulative returns of Top-10 buy&hold portfolios for all methods (2023-01-01 to 2024-01-01). Our approach dominates over the full horizon and exceeds the equal-weight benchmark.
  • Figure 5: Counterfactual Analysis with different deletion ratios for Mask-Tex and Mask-Edge strategies, respectively.