AI Revolutionizes Forex Forecasting; Chinese Yuan Faces Onshore-Offshore Discrepancy

AI Revolutionizes Forex Forecasting; Chinese Yuan Faces Onshore-Offshore Discrepancy

AI Enhances Exchange Rate Predictability

A recent study titled “AI and Exchange Rate Predictability” by Amin Izadyar revisits the longstanding exchange rate disconnect puzzle, first documented by Meese and Rogoff in 1983. The research employs generative artificial intelligence (AI) models, specifically ChatGPT and DeepSeek, to forecast currency returns based on economic fundamentals. By analyzing a comprehensive dataset of economic data releases for major currency pairs, the study measures the fundamental strength of each currency. The AI-powered fundamentals exhibit significant cross-sectional predictive power. A simple trading strategy that goes long on currencies with strong fundamentals and short on those with weak fundamentals generates a Sharpe ratio exceeding 0.7 per annum. These excess returns remain significant even after controlling for traditional currency factors. To address concerns of look-ahead bias, the study conducts multiple exercises to ensure that predictability stems from AI reasoning rather than memorization. The research also explores potential sources of predictability and finds evidence that the Taylor rule framework, commonly used by central banks to set interest rates, is a key mechanism connecting exchange rates to economic fundamentals.

Chinese Yuan’s Onshore-Offshore Discrepancy

In another significant development, a study titled “One Currency, Two Forward Prices: The Onshore-Offshore Renminbi Puzzle” by Samuel Drapeau, Peng Luo, Xuan Tao, and Tan Wang examines the persistent and economically large discrepancy between the onshore (CNY) and offshore (CNH) forward prices of the Chinese Yuan. China’s unique approach to financial integration involves fostering a deliverable offshore Renminbi market alongside the segmented onshore market, creating two venues for closely related claims on the same currency. While spot prices are tightly linked, the study finds that CNY and CNH forwards display a significant discrepancy. The researchers develop a joint equilibrium model for spot and forward trading with transaction costs and segmented supply. In the benchmark case with common constant supply and deterministic costs, spot parity implies a forward differential with the wrong sign relative to the data. However, introducing random offshore stress, modeled as a jump in trading costs, overturns this benchmark while preserving tight spot parity. The model provides a semi-explicit representation in the CNY/CNH application and calibrates the observed forward discrepancy in terms of the market-implied likelihood and severity of offshore liquidity stress.

Implications for the Forex Market

These developments have profound implications for the forex market. The integration of AI into exchange rate forecasting offers traders and policymakers enhanced tools for predicting currency movements, potentially leading to more informed decision-making and improved risk management. However, the persistent discrepancy between the onshore and offshore forward prices of the Chinese Yuan highlights the complexities of currency markets, especially in economies with partial convertibility. Understanding these dynamics is crucial for investors and policymakers navigating the intricacies of the forex market.

Conclusion

The forex market is witnessing significant transformations driven by technological advancements and unique market structures. The application of AI in exchange rate forecasting marks a new era of predictive analytics, while the onshore-offshore discrepancy in the Chinese Yuan underscores the challenges in achieving currency parity. As these developments unfold, stakeholders must stay informed and adapt to the evolving landscape of global currency markets.