CAMEF: Causal-Augmented Multi-Modality Event-Driven Financial Forecasting by Integrating Time Series Patterns and Salient Macroeconomic Announcements

2025-02-07

AI Summary

Existing methods typically model textual or temporal data in isolation, failing to capture the causal mechanisms and multimodal dynamics between macroeconomic events and asset prices. To address this, we propose a causally enhanced multimodal forecasting framework. First, we construct a novel benchmark dataset spanning 2008–2024, comprising six categories of macroeconomic policy announcements and high-frequency real-market data across five asset classes. Second, we introduce an LLM-driven counterfactual event generation method to explicitly model intervention effects. Third, we design a unified Transformer architecture jointly trained for text semantic parsing, time-series modeling, and causal inference. Experiments demonstrate that our model significantly outperforms state-of-the-art baselines in predicting event impact magnitude, direction, and temporal lag. Ablation studies confirm the critical contributions of both the causal module and fine-grained event-type modeling.

Technology Category

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

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Accurately forecasting the impact of macroeconomic events is critical for investors and policymakers. Salient events like monetary policy decisions and employment reports often trigger market movements by shaping expectations of economic growth and risk, thereby establishing causal relationships between events and market behavior. Existing forecasting methods typically focus either on textual analysis or time-series modeling, but fail to capture the multi-modal nature of financial markets and the causal relationship between events and price movements. To address these gaps, we propose CAMEF (Causal-Augmented Multi-Modality Event-Driven Financial Forecasting), a multi-modality framework that effectively integrates textual and time-series data with a causal learning mechanism and an LLM-based counterfactual event augmentation technique for causal-enhanced financial forecasting. Our contributions include: (1) a multi-modal framework that captures causal relationships between policy texts and historical price data; (2) a new financial dataset with six types of macroeconomic releases from 2008 to April 2024, and high-frequency real trading data for five key U.S. financial assets; and (3) an LLM-based counterfactual event augmentation strategy. We compare CAMEF to state-of-the-art transformer-based time-series and multi-modal baselines, and perform ablation studies to validate the effectiveness of the causal learning mechanism and event types.

Problem

• forecasting macroeconomic events impact
• integrating textual and time-series data
• capturing causal relationships in finance

Innovation

• Integrates textual and time-series data
• Uses causal learning mechanism
• Applies LLM-based counterfactual augmentation