Sales and Stock Purchase Prediction System Using Trend Moment Method and FIS Tsukamoto

Abstract

The purpose of this research is to build decisions support model to predict sales and stock purchase using Trend Moment method and Tsukamoto Fuzzy Inference System. Trend moment is a simple statistical-based forecasting method widely used to forecast sales in a company using historical data. Tsukamoto is a fuzzy inference system that uses monotonic reasoning to determine output. The object of this research is sales and purchase data for Ice Cream X Depo Jambi products from August 2019 to April 2020. The study aims to build a decision support model web-based to predict sales and purchases of ice cream X stock at Jambi depots. Fuzzy Tsukamoto in this study will be used to predict product stock purchases after predicting future sales using trend moments. The system input is in product data form, data of ice cream sales history, and data of ice cream stock purchase. Sales history data will be use to calculate slope and constanta that will predict future sales trends. Stocks  purchase history data along with sales trend prediction value will be use to calculate the membership degree of fuzzy variables, perform the aggregation process on fuzzy rules, and then carry out the defuzzification process to produce output prediction values for future ice cream stock purchases. from the prediction model implemented in the decision support system, sales prediction data has an accuracy of 71% while stock purchase predictions have an accuracy of 85%.