Forecasting demand accurately is key to running an efficient supply chain, keeping inventories stocked to the ideal levels and fulfilling your customer orders. Analytics-based demand forecasting is more accurate than other approaches, allowing you to minimise money tied up in stock, avoid shortages at times of high demand and identify otherwise hidden inefficiencies. This algorithm trains an ensemble demand forecasting model, for use on intermittent data (i.e. data with a high proportion of values that are zero or missing).