Peramalan Data Indeks Harga Konsumen Berbasis Time Series Multivariate Menggunakan Deep Learning

Abstract

Multivariate Time Series based forecasting is a type of forecasting that has more than one criterion changes from time to time that it can forecast based on historical patterns of data sequences. The Consumer Price Index (CPI) issued regularly every month by the Statistics Indonesia calculated based on data observations. This study is a development of previous research that only used on type of algorithm to predict CPI value resulting poor of accuracy due to lack of architecture variations testing. This study developed a CPI forecasting model with a new approach about using several types of deep learning algorithms, namely LSTM, Bidirectional LSTM, and Multilayer Perceptron with architectural variations of the number of neurons and epochs. Furthermore, this study adapt ADDIE model of Research and Development method. Based on the results, the best accuracy is obtained from the LSTM Bidirectional with 10 neurons and 2000 epoch resulting 3,519 of RMSE value. Meanwhile, based on the average RMSE value for the whole test, LSTM gets the smallest average of RMSE followed Bidirectional LSTM and Multilayer Perceptron with the RMSE value 4,334, 5,630, 6,304 respectively.

Prediksi Jangka Pendek Jumlah Pariwisata Dengan Metode Wema Pada Parameter Multivalue Forecasting Provinsi Jawa Timur

“…Metode prediksi time series dengan multivalue forecasting atau multivariate forecasting merupakan jenis prediksi yang memiliki lebih dari satu atribut data yang berubah setiap waktunya, sehingga memungkinkan untuk menghasilkan prediksi yang lebih akurat daripada prediksi times series dengan singe value forecasting atau univariate forecasting [19]. Multivalue forecasting atau multivariate forecasting memungkinkan dalam melakukan prediksi yang memperhitungkan semua atribut yang berpengaruh pada atribut target prediksi, sehingga tingkat akurasi yang tinggi dapat diperoleh [20].…”

Improved LSTM Method of Predicting Cryptocurrency Price Using Short-Term Data

“…Multivariate Time Series Forecasting is a forecasting method where it is inherently assumed that the variables depend on each other [31]. In other words, this method uses more than one variable or changing criteria from time to time [32]. Using this, we expect the prediction results to be more accurate than univariate methods, i.e., based on only one variable [33].…”

Pemodelan dan Peramalan Data Ekspor Sektor Pertanian Menggunakan Model Vector Autoregressive (VAR)

“…Dalam analisis multivariate time series yang tentunya melibatkan lebih dari satu variabel, analisis data time series secara simultan dilakukan guna mendapatkan kesimpulan yang akurat tanpa meninggalkan unsur penting yaitu keberadaan variabel lain selain hanya bergantung terhadap faktor waktu semata. Peramalan pada data multivariate time series sendiri adalah peramalan yang menggunakan lebih dari satu kriteria atau variabel yang berubah dari waktu ke waktu [4].…”