Adaptive exponential smoothing versus conventional approaches for lumpy demand forecasting: case of production planning for a manufacturing line

摘要: Production planning in a lumpy demand environment can be tenuous, with potentially costly forecasting errors. This paper addresses the issue of selecting smoothing factor used models. We propose simple adaptive approach to replace conventional industrial practice choosing largely based on analyst or engineer's experience and subjective judgment. The Kalman filter developed this study processes measurements estimate state linear system utilises knowledge from states dynamics. Performances an array models that have been shown work well environments are compared respect proposed constant across spectrum scenarios. All using weighting function generate smaller errors than their counterpart...