Prediksi Indeks Harga Konsumen Komoditas Makanan Berbasis Cloud Computing Menggunakan Multilayer Perceptron

Abstract

Prediction technique is one of the areas in data mining where it finds patterns from a set of data lead to predictions in the future. Prediction in the economic field is a predominant prediction due to one of the parameters for the country development. The Consumer Price Index describes the level of consumption of goods and services in society that used as a reference for the inflation rate. Previously the majority of research that predicts the Consumer Index value only predicts the value of the Consumer Price Index itself as an input and output value. The study built a forecasting model by utilizing multi input variables, namely 28 types of daily staple food prices as input values to predict Consumer Price Index of Surabaya for the period 2014 to 2018 where the whole development predictions built the Amazon Cloud Services environment. The prediction system is built using Multilayer Perceptron algorithm with architectural variations of the number of neurons, epoch, and hidden layer. Based on the test results, the best accuracy with RMSE value 3,380 is generated by 2 hidden layers, the first and second hidden layers which have 10 of neurons respectively with 1000 epoch.