PERBANDINGAN WAKTU EKSEKUSI PERAMALAN HARGA KOMODITAS PANGAN MENGGUNAKAN SPARKR DAN R STUDIO

The arrival of the big data era with characteristics such as large volumes makes calculation execution time a concern when carrying out analytics processes, forecasting food commodity prices. This study aims to examine effect framework through use sparkR. test is carried by varying several deep learning models, namely multi-layer perceptron model and using price one from 2018 2020. results show that sparkR significantly shorter its compared R studio. testing influence MLP also two hidden layers maximum node 13 nodes in 1 2 produces longest only layer 5 or number 3.