Optimasi Algoritma Long Short-Term Memory Menggunakan Particle Swarm Optimization untuk Prediksi Tingkat Inflasi di Jawa Timur

Ardiyansyah, Moh. Angga (2025) Optimasi Algoritma Long Short-Term Memory Menggunakan Particle Swarm Optimization untuk Prediksi Tingkat Inflasi di Jawa Timur. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21081010004 - Cover.pdf Download (919kB)
	Text (Bab 1) 21081010004 - Bab 1.pdf Download (289kB)
	Text (Bab 2) 21081010004 - Bab 2.pdf Restricted to Repository staff only until 5 December 2027. Download (553kB)
	Text (Bab 3) 21081010004 - Bab 3.pdf Restricted to Repository staff only until 5 December 2027. Download (661kB)
	Text (Bab 4) 21081010004 - Bab 4.pdf Restricted to Repository staff only until 5 December 2027. Download (2MB)
	Text (Bab 5) 21081010004 - Bab 5.pdf Download (227kB)
	Text (Daftar pustaka) 21081010004 - Daftar pustaka.pdf Download (187kB)
	Text (Lampiran) 21081010004 - Lampiran.pdf Restricted to Repository staff only Download (251kB)

Abstract

Inflation is a key economic indicator that directly affects regional economic stability. East Java has experienced significant fluctuations in Year-on-Year (YoY) inflation, requiring an accurate prediction model to support policymaking. Traditional forecasting methods such as ARIMA and Triple Exponential Smoothing have limitations in capturing non-linear patterns in inflation data. This study proposes a Long Short-Term Memory (LSTM) model optimized using Particle Swarm Optimization (PSO) to improve the accuracy of YoY inflation prediction in East Java. The Dataset consisted of monthly inflation data from 2005–2024 obtained from the Central Statistics Agency (BPS). The research process included data normalization, sliding window formation, data splitting, model training, and hyperparameter optimization using PSO. Model performance was evaluated using RMSE, MAE, and MAPE. The results show that the LSTM-PSO model achieved the best performance with RMSE 0.2171, MAE 0.4659, and MAPE 11.3892%, outperforming the baseline LSTM and other comparison models (ARIMA, TES, and GRU). These findings demonstrate that hyperparameter optimization via PSO significantly improves prediction accuracy and can serve as an analytical tool for policymakers in formulating price control strategies.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Haromainy, Muhammad Muharrom al	NIDN0701069503	muhammad.muharrom.if@upnjatim.ac.id
Thesis advisor	Junaidi, Achmad	NIDN0710117803	achmadjunaidi.if@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming
Q Science > QA Mathematics > QA76.87 Neural computers
T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Moh. Angga Ardiyansyah

Date Deposited:

05 Dec 2025 08:42

Last Modified:

05 Dec 2025 08:42

URI:

https://repository.upnjatim.ac.id/id/eprint/47977