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.
Journal of Applied Econometrics , Year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
econ.EM 2verdicts
UNVERDICTED 2representative citing papers
Proposes adaptive and alternative algorithms to improve the computational efficiency of simulation smoothing for large mixed-frequency VARs in nowcasting applications.
citing papers explorer
-
MACROCAST: A Vintage-Consistent Time Series Foundation Model for Real-Time Macroeconomic Forecasting
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.
-
Simulation smoothing for nowcasting with large mixed-frequency VARs
Proposes adaptive and alternative algorithms to improve the computational efficiency of simulation smoothing for large mixed-frequency VARs in nowcasting applications.