A forecast that uses only information that would have been available at the forecast holdout data (assuming the values to be unknown) or to a situation in which the event has not yet occurred (pure ex ante). See Armstrong 2001d.
Armstrong, J. S. (2001d), “Evaluating forecasting
methods,” in J. S. Armstrong (ed.), Principles of Forecasting. Norwell,
MA: Kluwer Academic Press.