<![CDATA[Raw material inventory management is an important aspect of kitchen operations, especially in the culinary industry, which depends on the timely and efficient availability of stock. Inaccurate raw material ordering can result in excess costs, stockpiling, or shortages that affect service quality. Therefore, an intelligent system is needed that can accurately and automatically predict raw material requirements. This study aims to design a kitchen raw material application using the Artificial Neural Network (ANN) method and the Backpropagation algorithm as a method for automatically predicting order quantities. By using historical raw material data as input to train the model, analysis data obtained from the mean squared error, mean absolute error, and R squared error can be used to study demand patterns over time. The test results show that the ANN model with the backpropagation algorithm is capable of providing fairly accurate predictions of kitchen raw material requirements. The application created can also simplify the raw material ordering process by providing recommendations for effective purchase quantities. Thus, this system can help manage inventory more efficiently and based on data.]]>
Copyrights © 2025
