Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

Prediksi Inflasi di Kota Bandung Menggunakan Metode Extreme Learning Machine (ELM)

Authors: null Hasan Al-Askary Kabalmay; Marizsa Herlina;

Prediksi Inflasi di Kota Bandung Menggunakan Metode Extreme Learning Machine (ELM)

Abstract

Abstract. This study aims to predict monthly inflation in Bandung City using the Extreme Learning Machine (ELM) method. Inflation, which is an indicator of economic stability, is important for predicting effective policy making. Data in the form of a time series of monthly inflation from January 2001 to March 2025 is used with a sliding window technique of 12 months of input and 1 month of output. The data is normalized and divided into 80% training data and 20% testing data. The best ELM model uses 23 Hidden Layer neurons with a coefficient of determination R² of 0.9415 in training and 0.7054 in testing. The prediction for the next three months shows inflation results of 6.62% in April 2025, 6.55% in May 2025 and 6.25% in June 2025. These results show that ELM is effective and efficient in modeling non-linear inflation patterns in Bandung City, providing an important reference for policymakers and economic actors.Abstrak. Penelitian ini bertujuan memprediksi inflasi bulanan di Kota Bandung menggunakan metode Extreme Learning Machine (ELM). Inflasi yang merupakan indikator kestabilan ekonomi menjadi penting untuk diprediksi demi pengambilan kebijakan yang efektif. Data berupa deret waktu inflasi bulanan Januari 2001 sampai Maret 2025 digunakan dengan teknik sliding window 12 bulan input dan 1 bulan output. Data dinormalisasi dan dibagi menjadi 80% data training dan 20% data testing. Model ELM terbaik menggunakan 23 neuron hidden layer dengan nilai koefisien determinasi R² sebesar 0,9415 pada training dan 0,7054 pada testing. Prediksi tiga bulan ke depan menunjukkan hasil inflasi 6.62% pada April 2025, 6.55% pada Mei 2025 dan 6.25% pada Juni 2025. Hasil ini menunjukkan ELM efektif dan efisien dalam memodelkan pola non-linear inflasi Kota Bandung, memberikan referensi penting bagi pembuat kebijakan dan pelaku ekonomi.

Related Organizations
  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!