Ensemble approach for time series analysis in demand forecasting: Ensemble learning

Abstract

Demand forecasting for replenishment is one of the main issue for retail industry in terms of optimizing stocks, minimizing costs and also for reducing stock out problem. Better forecasting for demands, means maximizing sales and result with more revenue and profit for retailers. An other critical result of the stock out problem is of course dissatisfied customers and customer churn effect to retailers as well. Customers, in general do not wish to buy an equivalent product from different brands instead of their routine selections. There are of course many parameters which affect very seriously forecasting accuracy of consumer demands. For instance; seasonality, promotional effects, social events, new trends, unexpected crisis, terrorism, changes on weather conditions, commercial behavior of competitors at the market etc. In this study, new heuristic approach for ensemble methodology has been proved. It has been implemented in SOK Market. It is one of Turkey's hard discount retail chain with 4000 stores and replenishes 1500 SKUs to stores via 22 regional distribution centers. The results of this approach and how to take benefits of the powerful common minded demand forecasting in time series forecasting analysis have been showed.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 38 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.