Development of Decision Support System for Ordering Goods using Fuzzy Tsukamoto

Abstract

The determination of a number of items in the right number is very essential for a company, but in actual practice, it is not trivial task. There are many factors that influence them such as inventory and sales levels. If a number of the ordering goods is too slight or too much, it will effect in the fulfillment of consumer demand. One of the ways that can be used to predict a number of ordering goods is a Fuzzy Inference System (FIS) using Tsukamoto fuzzy logic method. Three variables that are used in this study, namely sales, inventory, and ordering or purchasing. The sales input variables are divided into 3 categories, namely down, constant, and rise. Then, inventory input variebles are divided into 3 categories, namely a slight, moderate and many, likewise ordering input variables also consists in 3 categories, namely less, constant, and increase. The next step is the combination of rules from all events, then performing inference and defuzzifikasi to find average centered. To prove the applied method against manual calculations are then implemented in the developed system. The results of the system calculation do not much different with the calculation results that are done by manually. This is proven by information in the table of Mean Squared Error (MSE) with error results of under 1. So, without prejudice to accuracy in the calculation, the system can be used to save time in determining the amount of the ordering goods. The proposed method can help for research object, in this case is retail company to determine a number of ordering goods.