EUR-USD Exchange Rate Forecasting Based on Information Fusion with Large Language Models and Deep Learning Methods

ArXiv ID: 2408.13214 “View on arXiv”

Authors: Unknown

Abstract

Accurate forecasting of the EUR/USD exchange rate is crucial for investors, businesses, and policymakers. This paper proposes a novel framework, IUS, that integrates unstructured textual data from news and analysis with structured data on exchange rates and financial indicators to enhance exchange rate prediction. The IUS framework employs large language models for sentiment polarity scoring and exchange rate movement classification of texts. These textual features are combined with quantitative features and input into a Causality-Driven Feature Generator. An Optuna-optimized Bi-LSTM model is then used to forecast the EUR/USD exchange rate. Experiments demonstrate that the proposed method outperforms benchmark models, reducing MAE by 10.69% and RMSE by 9.56% compared to the best performing baseline. Results also show the benefits of data fusion, with the combination of unstructured and structured data yielding higher accuracy than structured data alone. Furthermore, feature selection using the top 12 important quantitative features combined with the textual features proves most effective. The proposed IUS framework and Optuna-Bi-LSTM model provide a powerful new approach for exchange rate forecasting through multi-source data integration.

Keywords: Bi-LSTM, Optuna, Causality-Driven Feature Generator, Unstructured Data Integration, Sentiment Analysis, Foreign Exchange (FX)

Complexity vs Empirical Score

• Math Complexity: 4.0/10
• Empirical Rigor: 7.5/10
• Quadrant: Street Traders
• Why: The paper relies on standard deep learning architectures (Bi-LSTM) and LLM fine-tuning, with relatively simple mathematical formulations; however, it demonstrates strong empirical rigor through extensive benchmarking against baselines, hyperparameter optimization with Optuna, specific error reduction metrics (MAE, RMSE), and a clear data fusion pipeline.

  flowchart TD
    A["Research Goal<br>Forecast EUR/USD Exchange Rate"] --> B["Data Collection<br>News & Financial Indicators"]
    B --> C["Text Processing<br>LLM Sentiment & Movement Classification"]
    B --> D["Feature Selection<br>Top 12 Quantitative Features"]
    C --> E["IUS Framework Fusion<br>Text + Quantitative Features"]
    D --> E
    E --> F["Causality-Driven<br>Feature Generator"]
    F --> G["Optuna-Bi-LSTM<br>Model Optimization & Forecasting"]
    G --> H["Outcomes<br>Reduced MAE by 10.69% & RMSE by 9.56%<br>Multi-source data fusion superior to structured-only"]