PREDIKSI PENDAPATAN CARGO SERVICE CENTER TANGERANG CITY MENGGUNAKAN ARSITEKTUR LONG SHORT TERM MEMORY

This study proposes an income prediction using the Deep Learning algorithm, namely Long Short Term Memory (LSTM). The results of testing accuracy are measured using Root Mean Squarred Error (RMSE). The data in this study are income from one of the Garuda Indonesia Cargo branch offices, the Tangerang City Cargo Service Center (CSC). Data contains collections of goods delivery transactions every day. The data goes through 4 preprocessing processes, namely subtotal, outlier detection, difference and scaling. LSTM is used because the data to be processed is time series data. The results of this study indicate that the prediction results are quite good by finding the most optimal hyperparamter first