High Accuracy in Forex Predictions Using the Neural Network Method Based on Particle Swarm Optimization


In forex trading, trader has to predict the risk in forex transaction and how to gain or increase the pro_ts based on analysis. The purpose of this study is to predict the value of the USD against the IDR by comparing the neural network method with the neural network method based on Particle Swarm Optimization (PSO) to _nd out which level of accuracy is higher. This method was chosen by the author after reading several previous studies using PSO-based Neural Networks showing a higher level of accuracy compared to using Neural Networks without PSO-based. From the results of the study it was found that predictions using Neural Networks strengthened with PSO resulted in very high accuracy.


Bidang ilmu
Sistem Informasi


[1] Kusumodestoni R H and Suyatno S, 2015 Prediksi Forex Menggunakan Model Neural Network Simetris J.

Tek. Mesin, Elektro dan Ilmu Komput. 6, 2 p. 205.

[2] Engel C, 2016 Exchange rates, interest rates, and the risk premium Am. Econ. Rev. 106, 2 p. 436{474.

[3] Galeshchuk S, 2016 Neurocomputing 172 p. 446{452.

[4] Wirth R, 2000 CRISP DM Towards a Standard Process Model for Data Mining Proc. Fourth Int. Conf. Pract.

Appl. Knowl. Discov. Data Min. 24959 p. 29{39.

[5] Khashei M and Bijari M, 2010 An arti_cial neural network (p, d, q) model for timeseries forecasting Expert

Syst. Appl. 37, 1 p. 479{489.

[6] Kamruzzaman J and Sarker R A, 2003 Comparing ANN Based Models with ARIMA for Prediction of Forex

Rates 22, 2 p. 2{11.

[7] Philip A A, 2011 Arti_cial Neural Network Model for Forecasting Foreign Exchange Rate 1, 3 p. 110{118.

[8] Maknickien_e N and Maknickas A, 2012 Application of Neural Network for Forecasting of Exchange Rates and Forex Trading p. 122{127.

[9] William H Hidayatno A and Zahra A A, 2014 Aplikasi Jaringan Saraf Tiruan Perambatan Balik Untuk

Prakiraan Valuta GBP/USD Dalam Forex Trading Transient 3, 4 p. 1{8.

[10] Ibrahim A M and El-Amary N H, 2018 Particle Swarm Optimization trained recurrent neural network for

voltage instability prediction J. Electr. Syst. Inf. Technol. 5, 2 p. 216{228.

[11] Yang H et al., 2017 Particle swarm optimization and its application to seismic inversion of igneous rocks Int.

J. Min. Sci. Technol. 27, 2 p. 349{357.

[12] Chang J F and Hsieh P Y, 2011 Particle swarm optimization based on back propagation network forecasting

exchange rates Int. J. Innov. Comput. Inf. Control 7, 12 p. 6837{6847.