ANALISIS DAN PREDIKSI TOTAL PENJUALAN PRODUK DI SUPERMARKET MENGGUNAKAN LINEAR REGRESSION

Abstract

The development of information technology has encouraged the retail sector, particularly supermarkets, to utilize sales transaction data as a basis for more accurate and efficient decision-making. The increasing volume of transaction data requires the application of predictive analysis methods to estimate total sales in an objective and measurable manner. This study aims to analyze and predict total product sales in supermarkets using the Linear Regression algorithm, as well as to evaluate the performance of the resulting prediction model.

The dataset used in this research consists of supermarket transaction data, with unit price and quantity as independent variables, and total sales as the dependent variable. The research methodology includes data preprocessing, splitting the dataset into training and testing data, training the Linear Regression model using the Ordinary Least Squares (OLS) method, and evaluating the model performance using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R²).

The results show that the Linear Regression algorithm is able to model the relationship between unit price, quantity, and total sales with a good level of accuracy and relatively low prediction error. Furthermore, the developed model demonstrates adequate stability in predicting total sales on the testing data. The conclusion of this study is that Linear Regression is effective for predicting supermarket total sales and can be utilized as a sales analysis tool and a data-driven decision support system.