Skripsi

PERAMALAN NILAI IMPOR MIGAS DI INDONESIA MENGGUNAKAN METODE FUZZY TIME SERIES MODEL MARKOV CHAIN DENGAN ALGORITMA PARTICLE SWARM OPTIMIZATION UNTUK PERDAGANGAN INTERNASIONAL

---

This research aims to improve the accuracy of forecasting the value of oil and gas imports in Indonesia using the Fuzzy Time Series Markov Chain (FTSMC) method optimized with the Particle Swarm Optimization (PSO) algorithm. The FTSMC method is applied to analyze historical data of oil and gas imports and make predictions, while PSO is used to optimize model parameters. The results showed that the FTSMC model without PSO with the number of fuzzification = 8, and parameters D1 = 0 and D2 = 700, achieved a Mean Absolute Percentage Error (MAPE) value of 9.53%. After being optimized with PSO, with the number of iterations=100, number of particles=70, moment of inertia=0.2, c1=0.5 and c2=0.5 resulted in a MAPE of 9.45%, showing a slight increase in accuracy. Although the difference was small, PSO optimization proved to be able to marginally improve model performance. This research shows that PSO optimization can be applied to improve the forecasting accuracy of oil and gas import values and is relevant for applications in the field of international trade. Keywords: Fuzzy Time Series Markov Chain, Particle Swarm Optimization, Forecasting, MAPE, import value.

---

Availability

Detail Information

Series Title

-

Call Number

T1582272024

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2024

Collation

xiv, 58 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

333.790 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Impor minyak dan gas bumi — Indonesia

Specific Detail Info

-

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment