Fuzzy Inference System as a Method of Determining Drug Demand in Pharmacy Systems

Abstract

In providing health services, puskesmas cannot be separated from the need for pharmaceutical preparations. Given the large influence of pharmaceutical preparations on the smoothness and performance of services at the puskesmas, it is necessary to pay special attention to managing them. However, prediction of demand is often difficult for officers, because it cannot be done by just anyone. Therefore, this study was conducted to provide consideration for the demand for pharmaceutical preparations in order to minimize the lack of pharmaceutical preparations. In the process, a demand analysis is carried out based on the number of uses and remaining inventory from the previous time period, to produce a prediction of the number of requests for pharmaceutical preparations. The method that will be used in this research is the Mamdani model fuzzy inference system, with interval determination based on the quartile method and the decile method. Which results obtained that the evaluation of predictive competence using both methods is sufficient. Namely, the Mean Absolute Percentage Error (MAPE) of the two methods is 26.43% for the decile method and 28.77% for the quartile method.