Exchange rate expectations and explainable AI
- This paper examines the determinants of long-term exchange rate expectations using survey data for advanced and emerging economies. We complement standard regressions with explainable machine learning (XGBoost with SHAP values) to capture nonlinearities and interactions. We find substantial differences across country groups, with inflation forecast errors and uncertainty more important in emerging markets. Monetary policy shocks become relevant once nonlinearities are accounted for. Overall, the results highlight state-dependent expectation formation and the value of explainable machine learning as a complement to standard methods.
| Author: | Theo BergerORCiDGND, Robert L. CzudajORCiD, Reyhaneh Rezaei Khavas |
|---|---|
| URN: | urn:nbn:de:bsz:960-opus4-39701 |
| DOI: | https://doi.org/10.25968/opus-3970 |
| DOI original: | https://doi.org/10.1016/j.frl.2026.110441 |
| ISSN: | 1544-6123 |
| Parent Title (English): | Finance Research Letters |
| Publisher: | Elsevier BV |
| Document Type: | Article |
| Language: | English |
| Year of Completion: | 2026 |
| Publishing Institution: | Hochschule Hannover |
| Release Date: | 2026/09/25 |
| Tag: | Exchange rate expectations; Monetary policy; Survey data; UIP; XGBoost |
| GND Keyword: | WechselkursGND; Künstliche IntelligenzGND; GeldpolitikGND |
| Volume: | 108 |
| Article Number: | 110441 |
| Page Number: | 7 |
| Institutes: | Fakultät IV - Wirtschaft und Informatik |
| DDC classes: | 330 Wirtschaft |
| Licence (German): |  Creative Commons - CC BY - Namensnennung 4.0 International |
