A Methodology to Forecast the Demand and Classify Inventories in Wholesale Supplier Companies
Keywords:
demand forecasting, aggregate planning, artificial neural networks, inventory classification, ABC classificationAbstract
Objective: To recommend a methodology that allows for inventory classification and demand forecast, by wholesale supplier companies, as critical factors to implement performance optimization.
Methods and techniques: The methodology relies on the use of a multilayer artificial neural network developed with Weka software, which adds the solution of inventory item classification problems, based on ABC and Analysis of hierarchical processes (AHP). The methodology was developed in three phases, the first one was in charge of inventory classification, the second was engaged in forecasting, and the third, in integrated result analysis.
Main results: A hierarchical scale of variables was suggested for inventory item classification, as well as weighing opinions and sub-opinions in it, and its selection scope. An effective way of forecasting individual demands was presented for every inventory item.
Conclusions: The application of this methodological tool by ACINOX sales company in Holguin province corroborated its effectiveness to solve inventory classification problems and demand forecasting. Deriving from the application, all the executives have access to a tool that contributes to decision-making, in order to favor better classified items and their forecasts.