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

2026-03-12

AI Summary

This work proposes an auditable, knowledge graph–based forecasting framework to address the lack of interpretability and structured reasoning in stock trend prediction. The approach leverages temporally grounded rules with clear economic meaning to guide multi-hop reasoning, constructs evidence chains over dynamic graphs, and fully grounds each inference path in news text. Large language models are integrated to assist decision-making, enabling end-to-end interpretable predictions. Evaluated on the S&P 500 benchmark, the model achieves 55.1% accuracy, 55.7% precision, 71.5% recall, and a 60.8% F1 score, significantly outperforming existing graph-based baselines and demonstrating a dual advantage in both predictive performance and interpretability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Knowledge Acquisition
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for 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 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.

Problem

• stock movement prediction
• knowledge graphs
• interpretability
• temporal reasoning
• explainable AI

Innovation

• knowledge graph
• interpretable prediction
• rule-guided reasoning
• multi-hop exploration
• LLM-guided decision making