Analisis Metode Rbf-Nn Dan Grnn Pada Peramalan Mata Uang EUR/USD

Ayuni Harianti, Nengah Widiangga

Abstract


Penelitian ini merupakan lanjutan dari penelitian sebelumnya tentang peramalan EUR/USD menggunakan metode RBF-NN (Radial Basis Function – Neural Network) yang diop­timasi dengan Algoritma Genetika. Metode yang ditambahkan adalah GRNN (Generalized Regression Neural Network). Sistem RBF-NN dapat diterapkan pada data dengan karakteristik nonlinear dan fluktuatif seperti data EUR/USD, sementara GRNN dapat bekerja dengan baik jika data training tersedia dalam jumlah banyak. Tingkat keakuratan dari peramalan di­tun­jukkan lewat nilai MAPE (Mean Absolut Percentage Error). Dari hasil percobaan, metode GRNN tidak memiliki nilai MAPE yang lebih baik daripada RBF-NN baik pada data daily low maupun data daily high. Teknik pencarian algorima genetika di dekat bobot RBF-NN terbukti lebih efektif daripada pen­dekatan fungsi GRNN dengan spread kecil pada kasus mata uang EUR/USD.

Keywords


EUR/USD; RBF-NN; Algo¬ritma Genetika; GRNN; MAPE; spread; daily high; daily low

Full Text:

PDF

References


Huda, F. A., Ridok. A., Dewi. C., 2013, Peramalan Time Series Saham Menggunakan Backpropagation Neural Network Berbasis Algoritma Genetika, Teknik Informatika PTIIIK, Universitas Brawijaya.

Bank for International Settlements, 2014. Triennial Central Bank Survey. Monetary and Economic Department.

Georgios Sermpinis, Konstantinos Theofilatos, Andreas Karathanasopoulos, Efstratios F. Georgopoulos, Christian Dunis, 2012. Forecasting Foreign Exchange Rates with Adaptive Neural Networks Using Radial-Basis Functions and Particle Swarm Optimization. European Journal Operation Research 225, 528–540. doi:http://dx.doi.org/10.1016/j.ejor.2012.10.020

Zuliana, S.U., 2012. Penerapan Global Ridge-Regression Pada Peramalan Data Time Series Non Linear Studi Kasus : Pemodelan Nilai Tukar US Dollar Terhadap Rupiah. Kaunia VIII

Warda, S. M., Irhamni F., 2012. Analisa Data Antaran Pos Express Menggunakan Metode Radial Basis Function Neural Network (RBF-NN) Study PT. POS Indonesia (Persero) Surabaya. Universitas Trunojoyo.

Maillard, E.P., Gueriot, D., 1997. RBF neural network, basis functions and genetic algorithm, in: International Conference on Neural Networks,1997. Presented at the International Conference on Neural Networks,1997, pp. 2187–2192 vol.4. doi:10.1109/ICNN.1997.614247

Wiharto, Y.S. Palgunadi, Muh Aziz Nugroho, 2013. Analisis Penggunaan Algoritma Genetika Untuk Perbaikan Jaringan Syaraf Tiruan Radial Basis Function. Seminar Nasional Teknologi Informasi Dan Komunikasi 2013. SENTIKA 2013.

Gautama, N.W., Dharma, A., Sudarma, M., 2016. Analisis Metode Rbf-Nn Dengan Optimasi Algoritma Genetika Pada Peramalan Mata Uang EUR/USD. Majalah Ilmiah Teknologi Elektro 15, 107–114.

Specht, D.F., 1991. A General Regression Neural Network. IEEE Transactions on Neural Network. 2, 568–576. doi:10.1109/72.97934

Heriyanto, D. N., Rachman, F.H., Satoto, B.D., 2013. Penerapan Metode Radial Basis Function Network dengan K-Means Cluster untuk Peramalan Kebutuhan Straw. Jurnal Sarjana Teknik Informatika. Universitas Trunojoyo Madura 1, 1–10.

Andreasson, N., Evgrafov, A., Patriksson, M., 2006. Introduction to Continuous Optimization: Foundations and Fundamental Algorithms, 1st edition. Studentlitteratur AB.

Dharma, A., Robandi, I., Purnomo, M.H., 2011. Application of Interval Type-2 Fuzzy Logic System in Short Term Load Forecasting on Special Days. IPTEK Journal for Technology and Science 22. doi:10.12962/ j20882033.v22i2.65

Gang Sun, Steven J Hoff, Brian C Zelle, Minda A Smith, 2008. Development and Comparison of Backpropagation and Generalized Regression Neural Network Models to Predict Diurnal and Seasonal Gas and PM10 Concentrations and Emissions from Swine Buildings. American Society of Agricultural and Biological Engineers. doi:10.13031/2013.25180

Yazıcı, G., Polat, Ö., Yıldırım, T., 2006. Genetic Optimizations for Radial Basis Function and General Regression Neural Networks, in: Gelbukh, A., Reyes-Garcia, C.A. (Eds.), MICAI 2006: Advances in Artificial Intelligence, Lecture Notes in Computer Science. Presented at the Mexican International Conference on Artificial Intelligence, Springer Berlin Heidelberg, pp. 348–356.




DOI: https://doi.org/10.47532/jiv.v5i1.413

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Jurnal Ilmiah Vastuwidya Indexed By :

Jurnal Ilmiah Vastuwidya site and its metadata are licensed under CC BY-SA

View My Stats