LAUSR

The need for food supplies are very crucial in a food business, therefore it is necessary to estimate the right supplies to maximize profit. One of the methods to determine these is by looking for patterns and forecasting transaction data. The purpose of this research is to estimate the gourami supplies using transaction data to forecast using the gradient boosting decision tree method from XGBoost. The transaction data used comes from Restaurant X with a time period from 2016 to 2019. A measurement error rate of the model is achieved by using MAE (Mean Absolute Error) and MAPE (Mean Absolute Percentage Error). This study tried five XGBoost models with different features such as lag, rolling window, mean encoding, and mix. The results of this study indicate that the mixed feature model produces an accuracy of 97.54% with an MAE of 0.63 and a MAPE of 2.64%.