-driven demand. This method directly considers feature information such as promotions and trends to make periodic order decisions …, does not require distributional assumptions on demand, and is sample efficient. The application of supervised learning in … classical setting with stationary demand, and it can outperform them in non-stationary settings where demand is driven by …

Safety stock is necessary for firms in order to manage the uncertainty of demand. A key component in its determination … is the estimation of the variance of the forecast error over lead time. Given the multitude of demand processes that lack … issue of these correlations first by demonstrating their existence for some fundamental demand processes, and second by …