Neuro-Fuzzy Model of Reliability Evaluation of the Sales Planning

The article is devoted to the application of the theory of fuzzy sets and neural networks to evaluate the degree of reliability in purchases and sales planning. Moreover, this article describes the model of separation of reliability levels depending on the sales stability, correctness of the selected interval and frequency of planning. The stability of sales is a key indicator allowing manager to decide about carrying out planning “by hand”. Automatic planning of purchases for future periods is possible if the sales for the prior period are stable. The result is a description of the configuration of a neuro-fuzzy network, in order to make a decision about the level of planning reliability. During this study the neuro-fuzzy network is trained on real sales data from a large trade and purchasing enterprise.