Research

Paper

AI LLM March 12, 2026

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

Authors

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.

Metadata

arXiv ID: 2603.12500
Provider: ARXIV
Primary Category: cs.CE
Published: 2026-03-12
Fetched: 2026-03-16 06:01

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.12500v1</id>\n    <title>TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction</title>\n    <updated>2026-03-12T22:41:53Z</updated>\n    <link href='https://arxiv.org/abs/2603.12500v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.12500v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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\\&amp;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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CE'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-12T22:41:53Z</published>\n    <arxiv:primary_category term='cs.CE'/>\n    <author>\n      <name>Qianggang Ding</name>\n    </author>\n    <author>\n      <name>Haochen Shi</name>\n    </author>\n    <author>\n      <name>Luis Castejón Lozano</name>\n    </author>\n    <author>\n      <name>Miguel Conner</name>\n    </author>\n    <author>\n      <name>Juan Abia</name>\n    </author>\n    <author>\n      <name>Luis Gallego-Ledesma</name>\n    </author>\n    <author>\n      <name>Joshua Fellowes</name>\n    </author>\n    <author>\n      <name>Gerard Conangla Planes</name>\n    </author>\n    <author>\n      <name>Adam Elwood</name>\n    </author>\n    <author>\n      <name>Bang Liu</name>\n    </author>\n  </entry>"
}