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

arXiv: https://arxiv.org/abs/2603.12500 · HTML: https://mlsanity.com/paper/2603.12500/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 49 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design](https://mlsanity.com/paper/2311.13743/) (2023)
- [FinBERT: A Pretrained Language Model for Financial Communications](https://mlsanity.com/paper/2006.08097/) (2020)
- [Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs](https://mlsanity.com/paper/1705.05742/) (2017)
- [Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering](https://mlsanity.com/paper/2306.04136/) (2023)
- [RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2010.04029/) (2020)
- [Multi-Hop Knowledge Graph Reasoning with Reward Shaping](https://mlsanity.com/paper/1808.10568/) (2018)
- [Temporal Relational Ranking for Stock Prediction](https://mlsanity.com/paper/1809.09441/) (2018)
- [Boosting Language Models Reasoning with Chain-of-Knowledge Prompting](https://mlsanity.com/paper/2306.06427/) (2023)
- [FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets](https://mlsanity.com/paper/2310.04793/) (2023)
- [HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction](https://mlsanity.com/paper/1908.07999/) (2019)
- [Reinforced Anytime Bottom Up Rule Learning for Knowledge Graph Completion](https://mlsanity.com/paper/2004.04412/) (2020)
- [RAG-KG-IL: A Multi-Agent Hybrid Framework for Reducing Hallucinations and Enhancing LLM Reasoning through RAG and Incremental Knowledge Graph Learning Integration](https://mlsanity.com/paper/2503.13514/) (2025)
- [MARS: A Meta-Adaptive Reinforcement Learning Framework for Risk-Aware Multi-Agent Portfolio Management](https://mlsanity.com/paper/2508.01173/) (2025)

## Built on by (most cited first, 1 of 1)

- [RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting](https://mlsanity.com/paper/2609.34004/) (2026)

## Abstract (arXiv)

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 textttUP/textttDOWN 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.