ANALISIS REGRESI LINEAR DAN MOVING AVERAGE DALAM MEMPREDIKSI DATA PENJUALAN SUPERMARKET

Abstract

Sales in supermarkets during the Covid 19 pandemic will change normally. Sales in normal times may always be crowded and a lot. It is different during a pandemic because several layers of society experience economic difficulties. Supermarkets that cannot solve this problem may have a loss or may have to close temporarily. From this background, we propose a predictive analysis of sales of electronic and health goods in supermarkets using Linear Regression and Moving Average methods. The data used in this research were taken from the Kaggle dataset website. The data consists of several types of goods, but we use the electronics and health categories. The purpose of this research to analyze the two algorithms in predicting electronic sales and health data. The tool used to help analyze is python. How to analyze the two algorithms with MSE (Mean Square Error) and RMSE. The results of the analysis show that the Moving Average method has the best performance as evidenced by the MSE and RMSE values ​​of electronic data which are 57,603, 7.59, health data are 50,489, 7,106. While the linear regression method prediction results on electronic data and health, the MSE and RMSE values ​​are 114.79, 10.71, 59.965, 7,744.