History Rhymes: Macro-Contextual Retrieval for Robust Financial Forecasting

2025-11-12

AI Summary

Financial markets exhibit non-stationarity and structural breaks, causing severe performance degradation of predictive models under out-of-distribution (OOD) conditions. To address this, we propose a macroeconomic context retrieval framework that jointly embeds macroeconomic indicators (CPI, unemployment rate, interest rate spreads, GDP) and news sentiment into a unified similarity space—enabling zero-shot, causally grounded case retrieval and interpretable evidence-chain construction. By retrieving historically analogous macroeconomic regimes, our method enhances forecasting robustness against train-deploy distribution shifts. In 2024 out-of-sample tests on AAPL and XOM, the resulting trading strategy demonstrates strong robustness (AAPL: Profit Factor = 1.18, Sharpe Ratio = 0.95; XOM: Profit Factor = 1.16, Sharpe Ratio = 0.61), consistently outperforming static and state-of-the-art multimodal baselines. Our key contributions are: (i) a novel multi-source macro-text joint embedding mechanism; and (ii) an OOD-robust, interpretable retrieval-augmented forecasting paradigm.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Financial markets are inherently non-stationary: structural breaks and macroeconomic regime shifts often cause forecasting models to fail when deployed out of distribution (OOD). Conventional multimodal approaches that simply fuse numerical indicators and textual sentiment rarely adapt to such shifts. We introduce macro-contextual retrieval, a retrieval-augmented forecasting framework that grounds each prediction in historically analogous macroeconomic regimes. The method jointly embeds macro indicators (e.g., CPI, unemployment, yield spread, GDP growth) and financial news sentiment in a shared similarity space, enabling causal retrieval of precedent periods during inference without retraining. Trained on seventeen years of S&P 500 data (2007-2023) and evaluated OOD on AAPL (2024) and XOM (2024), the framework consistently narrows the CV to OOD performance gap. Macro-conditioned retrieval achieves the only positive out-of-sample trading outcomes (AAPL: PF=1.18, Sharpe=0.95; XOM: PF=1.16, Sharpe=0.61), while static numeric, text-only, and naive multimodal baselines collapse under regime shifts. Beyond metric gains, retrieved neighbors form interpretable evidence chains that correspond to recognizable macro contexts, such as inflationary or yield-curve inversion phases, supporting causal interpretability and transparency. By operationalizing the principle that"financial history may not repeat, but it often rhymes,"this work demonstrates that macro-aware retrieval yields robust, explainable forecasts under distributional change. All datasets, models, and source code are publicly available.

Problem

• Forecasting financial markets under non-stationary macroeconomic regime shifts
• Addressing model failure when deployed out-of-distribution due to structural breaks
• Improving robustness against distributional changes in financial time series

Innovation

• Retrieves historically analogous macroeconomic regimes for predictions
• Embeds macro indicators and news sentiment in shared space
• Enables causal retrieval without retraining during inference