PREDIKSI TIME SERIES TINGKAT INFLASI INDONESIA MENGGUNAKAN EVOLUTION STRATEGIES
DOI:
https://doi.org/10.33197/jitter.vol1.iss2.2015.49Abstract
[INA]
Prediksi tingkat inflasi bisa dilakukan dengan cara mempelajari data historis masa lalu yang dinamakan dengan metode prediksi data time series. Permasalahan pencarian model prediksi yang paling optimal berdasarkan pola data historis ini dapat dipandang sebagai sebuah permasalahan optimasi untuk mencari model prediksi yang menghasilkan tingkat error prediksi paling kecil. Evolution Staregies (ES) sering digunakan untuk menyelesaikan masalah-masalah optimasi numerik seperti itu. Oleh karena itu, pada penelitian ini dilakukan prediksi time series tingkat inflasi Indonesia dengan menggunakan ES.
Berdasarkan penelitian yang telah dilakukan dapat diketahui bahwa akurasi prediksi yang didapatkan kurang optimal, dengan MAPE 6.54%. Hal ini dikarenakan data historis tingkat inflasi di Indonesia sangat fluktuatif. Namun untuk pola data linear, ES bisa mendapatkan hasil prediksi yang akurat.
[EN]
The inflation rate can be predicted by studying the history of past data, called time series prediction method. Problem in finding optimal prediction model based on historical data can be viewed as an optimization problem to find a predictive model that resulting the smallest prediction error rate. Evolution Staregies (ES) is often used to solve numerical optimization problems like that. Therefore, in this study was performed Indonesian inflation rate time series prediction using ES.
Based on the study can be seen that the accuracy of prediction was less than optimal, with MAPE 6.54%. This was because the historical data of Indonesia inflation rate was very fluctuative. However, for linear data pattern, ES can obtain accurate prediction.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Submission of a manuscript implies that the submitted work has not been published before (except as part of a thesis or report, or abstract); that it is not under consideration for publication elsewhere; that its publication has been approved by all co-authors. If and when the manuscript is accepted for publication, the author(s) still hold the copyright and retain publishing rights without restrictions. Authors or others are allowed to multiply the article as long as not for commercial purposes. For the new invention, authors are suggested to manage its patent before published. The license type is CC-BY-SA 4.0.