PENINGKATAN AKURASI PREDIKSI PENGADAAN BAHAN BAKU PRODUKSI DENGAN MENGGUNAKAN METODE NEURAL NETWORK

Abstract

Forecasting or prediction in production activities is an activity that aims to predict everything related to production, supply, demand, and use of technology in an industry. In the end, this prediction is often used by companies and operational management to make plans related to their business activities in certain periods. As a tool for measuring the level of predictions that are close to good accuracy which can be used as a reference for calculating a business process in the future, companies also need an accurate and tested measuring tool based on the type of estimate itself. The NEURAL NETWORK  method with backpropagation calculates a pattern based on the history of several periods that have occurred. This method is often used to obtain prediction accuracy in forecasting activities. Inaccurate packaging stock inventory forecasting to support production needs causes the inventory space to exceed capacity and the production process is disrupted, so the selection of an appropriate forecasting method is needed. The use of the NEURAL NETWORK  method with backpropagation to increase the accuracy of the prediction of the procurement of packaged goods in this study is very suitable. Results of Data Training with input data for begin stock, consumption, incoming, and safety stock and target data is the stock order yields the best MSE value of 0.03603642 on the number of neurons 11 with an epoch value of 1000 and a maximum error limit of 6, so that the test data resulted in the accuracy of the MAPE value of 0.52%.