美联储-美德还是幻影？汇率预测的复杂性（英）

Finance and Economics Discussion SeriesFederal Reserve Board, Washington, D.C.ISSN 1936-2854 (Print)ISSN 2767-3898 (Online)Virtue or Mirage? Complexity in Exchange Rate PredictionRehim Kilic2025-089Please cite this paper as:Kilic, Rehim (2025). “Virtue or Mirage? Complexity in Exchange Rate Prediction,” Financeand Economics Discussion Series 2025-089. Washington: Board of Governors of the FederalReserve System, https://doi.org/10.17016/FEDS.2025.089.NOTE: Staff working papers in the Finance and Economics Discussion Series (FEDS) are preliminarymaterials circulated to stimulate discussion and critical comment. The analysis and conclusions set forthare those of the authors and do not indicate concurrence by other members of the research staff or theBoard of Governors. References in publications to the Finance and Economics Discussion Series (other thanacknowledgement) should be cleared with the author(s) to protect the tentative character of these papers.Virtue or Mirage? Complexity in Exchange RatePredictionRehim Kılıç∗September 16, 2025AbstractThis paper investigates whether the “virtue of complexity” (VoC), documentedin equity return prediction, extends to exchange rate forecasting. Using nonlinearRidge regressions with Random Fourier Features (Ridge–RFF), we compare the predic-tive performance of complex models against linear regression and the robust randomwalk benchmark. Forecasts are constructed across three sets of economic fundamen-tals—traditional monetary, expanded monetary and non-monetary, and Taylor-rulepredictors—with nominal complexity varied through rolling training windows of 12, 60,and 120 months. Our results offer a cautionary perspective. Complexity delivers onlymodest, localized gains: in very small samples with rich predictor sets, Ridge–RFF canoutperform linear regression. Yet these improvements never translate into systematicgains over the random walk. As training windows expand, Ridge–RFF quickly losesground, while linear regression increasingly dominates, at times even surpassing therandom walk under expanded fundamentals. Market-timing analyses reinforce thesefindings: complexity-based strategies yield occasional short-sample gains but are unsta-ble and prone to sharp drawdowns, whereas simpler linear and random walk strategiesprovide more robust and consistent economic value. By incorporating formal forecastevaluation tests—including Clark–West and Diebold–Mariano—we show that apparentgains from complexity are fragile and rarely statistically significant. Overall, our evidencepoints to a limited virtue of complexity in FX forecasting: complexity may help undernarrowly defined conditions, but parsimony and the random walk benchmark remainmore reliable across samples, predictor sets, and economic evaluations.JEL Classification: F41, C50, G11, G15.Keywords: Foreign exchange rate, Exchange rate disconnect puzzle, predictability, complexity,machine learning, Ridge, RFF.∗Federal Reserve Board, Washington, DC E-mail: rehim.kilic