Food and Beverage Sales Prediction Using Linear Regression and Random Forest Regression at Ayam Serayu Restaurant Bekasi

Abstract

The large number of sales transactions at Ayam Serayu Restaurant Bekasi creates challenges in managing and analyzing sales data. Manual processes make it difficult to predict future sales, affecting inventory management and decision-making. Therefore, an accurate prediction method is needed. This study applies Linear Regression and Random Forest Regression to predict sales based on historical data. The research stages included data collection, preprocessing, modeling, and evaluation using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The results show that Random Forest Regression provides better accuracy than Linear Regression. The resulting model is expected to improve operational efficiency and support decision-making at Ayam Serayu Restaurant Bekasi.