用因果发现+概率预测，精准预判失业率并识别异常
Methodological Insights into Structural Causal Modelling and Uncertainty-Aware Forecasting for Economic Indicators
- 用LPCMCI+GPDC挖掘经济指标间动态因果关系
- 零样本预测失业率，两季度前瞻准确率高，置信区间可靠
- 适合政策制定者和金融分析师参考，提升预测稳健性
本文结合因果发现与不确定性感知预测，提出一种金融时间序列分析方法。以1970至2021年美国季度数据为案例，研究GDP、经济增长、通胀和失业率四个关键宏观经济指标。采用LPCMCI框架与高斯过程距离相关（GPDC）揭示动态因果关系：经济增长对GDP存在稳健的单向因果影响；通胀连接较弱，暗示潜在因素干扰；失业率表现出强自回归依赖性，适合作为概率预测研究对象。利用专为时序训练的大型语言模型Chronos，在无任务微调情况下实现失业率的零样本预测，成功预测未来一季和两季的趋势。模型输出90%置信区间，支持基于统计原理的异常检测。研究表明，将因果结构学习与概率语言模型结合，有助于优化经济政策决策并增强预测鲁棒性。
原文摘要 · Abstract (English)
This paper presents a methodological approach to financial time series analysis by combining causal discovery and uncertainty-aware forecasting. As a case study, we focus on four key U.S. macroeconomic indicators -- GDP, economic growth, inflation, and unemployment -- and we apply the LPCMCI framework with Gaussian Process Distance Correlation (GPDC) to uncover dynamic causal relationships in quarterly data from 1970 to 2021. Our results reveal a robust unidirectional causal link from economic growth to GDP and highlight the limited connectivity of inflation, suggesting the influence of latent factors. Unemployment exhibits strong autoregressive dependence, motivating its use as a case study for probabilistic forecasting. Leveraging the Chronos framework, a large language model trained for time series, we perform zero-shot predictions on unemployment. This approach delivers accurate forecasts one and two quarters ahead, without requiring task-specific training. Crucially, the model's uncertainty-aware predictions yield 90\% confidence intervals, enabling effective anomaly detection through statistically principled deviation analysis. This study demonstrates the value of combining causal structure learning with probabilistic language models to inform economic policy and enhance forecasting robustness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。