MACROCAST is the first leakage-free time series foundation model for real-time macroeconomic forecasting, trained exclusively on synthetic series and vintage data, outperforming AR(1), Chronos-2, BVAR, and DFM benchmarks on FRED-MD.
Economics Letters , Year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Extends GAS Markov-switching to K regimes, shows via simulation that means/variances/transitions recover reliably but TVTP coefficients and GAS score parameter are hard to identify, and finds lagged-yield-level transitions fit Treasury data best while GAS fails to converge.
citing papers explorer
-
Multi-regime Markov-switching models with time-varying transition probabilities: An application to U.S. Treasury yields
Extends GAS Markov-switching to K regimes, shows via simulation that means/variances/transitions recover reliably but TVTP coefficients and GAS score parameter are hard to identify, and finds lagged-yield-level transitions fit Treasury data best while GAS fails to converge.