AI and Exchange Rate Predictability
创建于 更新于
摘要
This paper revisits the exchange rate disconnect puzzle using generative AI to forecast currency returns from economic fundamentals. Employing ChatGPT and DeepSeek, a comprehensive dataset of 544 indicators spanning 1996–2024 is analyzed to extract AI-derived fundamentals, showing significant cross-sectional predictability across major currencies. A simple AI-driven AIFX strategy—going long currencies with strong fundamentals and short those with weak fundamentals—achieves an annualized Sharpe ratio above 0.7, with alpha that remains significant after controlling for standard FX factors. Multiple robustness checks (GPT-4o and DeepSeek-V3, weighted signals, and time-series specs) support the central results. Four look-ahead bias tests indicate the results arise from AI reasoning rather than memorization, and the Taylor-rule framework linking fundamentals to monetary policy emerges as a key mechanism behind the predictability. [page::1]
