Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation

2025-02-24

AI Summary

Financial bond yield forecasting faces three core challenges: data scarcity, nonlinear macroeconomic dependencies, and evolving market dynamics. To address these, we propose a liquidity-aware end-to-end prediction framework. First, we introduce a synthetic data generation paradigm jointly driven by a Causal Generative Adversarial Network (CausalGAN) and Soft Actor-Critic (SAC) reinforcement learning, constrained by 12 macroeconomic variables to ensure causal fidelity. Second, we fine-tune the Qwen2.5-7B large language model (LLM) to generate trading signals and perform multi-dimensional risk assessment. The method establishes a closed-loop “generation–reasoning–evaluation” pipeline, integrating automated, human, and LLM-based evaluation. Experiments demonstrate a mean absolute error (MAE) of 0.103%, a strategy profitability of 60%, and LLM and domain-expert evaluation scores of 3.37/5 and 4.67/5, respectively—substantially outperforming existing baselines. This work establishes a novel paradigm for high-fidelity risk control and intelligent investment decision-making.

Technology Category

• Machine Learning: Causal Learning
• Natural Language Processing: Generation
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• 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

Abstract

Financial bond yield forecasting is challenging due to data scarcity, nonlinear macroeconomic dependencies, and evolving market conditions. In this paper, we propose a novel framework that leverages Causal Generative Adversarial Networks (CausalGANs) and Soft Actor-Critic (SAC) reinforcement learning (RL) to generate high-fidelity synthetic bond yield data for four major bond categories (AAA, BAA, US10Y, Junk). By incorporating 12 key macroeconomic variables, we ensure statistical fidelity by preserving essential market properties. To transform this market dependent synthetic data into actionable insights, we employ a finetuned Large Language Model (LLM) Qwen2.5-7B that generates trading signals (BUY/HOLD/SELL), risk assessments, and volatility projections. We use automated, human and LLM evaluations, all of which demonstrate that our framework improves forecasting performance over existing methods, with statistical validation via predictive accuracy, MAE evaluation(0.103%), profit/loss evaluation (60% profit rate), LLM evaluation (3.37/5) and expert assessments scoring 4.67 out of 5. The reinforcement learning-enhanced synthetic data generation achieves the least Mean Absolute Error of 0.103, demonstrating its effectiveness in replicating real-world bond market dynamics. We not only enhance data-driven trading strategies but also provides a scalable, high-fidelity synthetic financial data pipeline for risk&volatility management and investment decision-making. This work establishes a bridge between synthetic data generation, LLM driven financial forecasting, and language model evaluation, contributing to AI-driven financial decision-making.

Problem

• Predict bond yields using CausalGANs and RL.
• Generate synthetic bond data for trading insights.
• Enhance financial forecasting with LLM and RL.

Innovation

• Uses CausalGANs for synthetic bond data
• Applies SAC reinforcement learning for accuracy
• Employs LLM for financial signal generation