Professor, Department of Computer Engineering, Odlar Yurdu University, Baku, Azerbaijan
*Corresponding Author: Ramiz Alekperov, Professor, Department of Computer Engineering, Odlar Yurdu University, Baku, Azerbaijan.
Received: April 26, 2021; Published: May 15, 2021
Determining the need for medicines and medical supplies is directly related to the characteristics of their products, their actual consumption, and the identification of patterns of changes in demand for them. This article discusses the use of fuzzy logic and a neural network to predict the demand for pharmaceutical products in a distributed network, in conditions of insufficient information, a large assortment, and the influence of risk factors. A comprehensive approach to solving forecasting problems is proposed using: the theory of fuzzy logic - when forecasting emerging and unmet needs and a neural network - if there is a lot of retrospective information about the actual sale of drugs. A method for fuzzy classification of drug demand using ABC and XYZ analysis is described. Using this approach to solve the problems of forecasting demand allows you to get statistics and experience. The general algorithm, mathematical interpretation, and examples of forecasting the demand for pharmaceutical products in the face of uncertainty of information are given, and the general structure of the system for forecasting the demand for drugs is described. A fragment of the program code for predicting the demand for drugs based on neural networks for cases with sufficient sales statistics is presented.
Keywords: Demand Forecasting; Pharmaceutical Market; Fuzzy Classification; Neural Networks; ABC Analysis; XYZ Analysis, Cross-analysis
Citation: Ramiz Alekperov. “Comprehensive Application of the Theory of Fuzzy Logic and Neural Networks to Predict the Demand for Drugs”.Acta Scientific Medical Sciences 5.6 (2021): 74-82.
Copyright: © 2021 Ramiz Alekperov. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.