Forecasting Indeks Harga Konsumen Kota Surabaya Menggunakan Metode Genetic Algorithm-Support Vector Regression

Nabilla, Putri Herliani (2024) Forecasting Indeks Harga Konsumen Kota Surabaya Menggunakan Metode Genetic Algorithm-Support Vector Regression. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003201014-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (3MB) | Request a copy

Abstract

Indeks Harga Konsumen menunjukkan ukuran harga rata-rata barang maupun jasa yang dikonsumsi oleh rumah tangga dalam kurun waktu tertentu. Indeks ini dipengaruhi berbagai faktor mulai dari gejolak harga jenis barang yang tidak menentu, nilai tukar rupiah, tingkat inflasi, kebijakan pemerintah dan permintaan masyarakat. Pertumbuhan angka Indeks Harga Konsumen dapat menggambarkan harga barang atau jasa kebutuhan masyarakat yang dapat mempengaruhi perekonomian negara. Salah satu metode yang digunakan untuk forecasting pergerakan nilai prediksi ini adalah Support Vector Regression (SVR). SVR merupakan metode menganalisis dengan mencari hyperplane terbaik suatu fungsi regresi. Dalam kasus ini menggunakan pendekatan kernel linear, polynomial, dan RBF, dimana dilakukan hibridisasi algoritma SVR dengan optimasi menggunakan Genetic Algorithm (GA) untuk meningkatkan akurasi peramalan. Kriteria evaluasi model menggunakan RMSE dan sMAPE selama enam bulan hingga menghasilkan model terbaik. Hasil peramalan cukup akurat pada model terbaik GA-SVR dengan parameter nilai RMSE dan sMAPE baik in sample maupun out sample lebih kecil dibandingkan SVR sebelum optimasi. Berdasarkan hasil peramalan diketahui bahwa Indeks Harga Konsumen Kota Surabaya menunjukkan stabilitas penurunan pada enam bulan mendatang. Dengan demikian, metode ini sudah tepat digunakan untuk meramalkan Indeks Harga Konsumen Kota Surabaya
====================================================================================================================================
The consumer price index shows a measure of the average price of goods and services consumed by households in a certain period of time. This index is influenced by various factors ranging from volatile price fluctuations for various types of goods, the rupiah exchange rate, inflation rate, government policy and public demand. The growth in consumer price index figures can describe the prices of goods or services needed by society. One of the methods used for forecasting the movement of predicted values is Support Vector Regression (SVR). SVR is an analysis method by finding the best hyperplane of regression function. In this case, used by a linear, polynomial and RBF kernel approach, where the SVR algorithm is hybridized with optimization using a Genetic Algorithm (GA) to increase forecasting accuracy. The model evaluation criteria used RMSE and sMAPE for six months to produce the best model. The forecasting results are accurate in the best GA-SVR model with the smallest RMSE and sMAPE parameter values both in sample and out sample compared to SVR before optimization. Based on forecasting results, it is known that the Surabaya consumer price index shows a stable decline for the next six months. Thus, this method is appropriate use to predict the consumer price index of Surabaya.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Forecasting, Indeks Harga Konsumen, Support Vector Regression, Genetic Algorithm
Subjects:	H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA30.3 Time-series analysis H Social Sciences > HB Economic Theory H Social Sciences > HB Economic Theory > Economic forecasting--Mathematical models. Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Putri Herliani Nabilla
Date Deposited:	11 Aug 2024 05:49
Last Modified:	11 Sep 2024 03:37
URI:	http://repository.its.ac.id/id/eprint/115072

Actions (login required)

View Item