Forecasting of currency exchange rates using ANN: a case study

Kamruzzaman, Joarder; Sarker, Ruhul A.

doi:10.1109/icnnsp.2003.1279395

Cited by 99 publications

(73 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Earlier studies (17) reported that an ANN based forex model trained with scaled conjugate gradient learning algorithm predicted currency exchange rate more accurately than standard backpropgation based learning algorithm, and both the models outperformed traditional ARIMA model. Superiority of ANN model over ARIMA has also been supported by other studies (32) .…”

Section: Resultsmentioning

confidence: 99%

“…The regularization parameter C was varied from 0.1 to 10 5 and parameter was varied from 0.0005 to 0.006 to investigate their effects on prediction and discussed later in this section. The forecasted result over the test data was compared with the Scaled Conjugate Gradient (SCG) neural network model studied by Kamruzzaman and Sarker (17) (18) . In that study, it was concluded that the scaled conjugate gradient based model was the best among the three neu-ral network models tested for predicting those currency exchange rates under consideration.…”

Section: Simulation Results and Discussionmentioning

confidence: 99%

“…But it has been demonstrated in numerous studies that standard BP is extremely slow and does not yield good generalization ability in many cases. The present study compares SVM model's performance with an ANN model trained with scaled conjugate gradient algorithm which was found to perform best among the NN models studied earlier (17) . The proposed model was used to predict currency exchange rates of Australian Dollar with six other currencies such as US Dollar (USD), Great Britain Pound (GBP), Japanese Yen (JPY), Singapore Dollar (SGD), New Zealand Dollar (NZD) and Swiss Franc (CHF).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Application of Support Vector Machine to Forex Monitoring

Sarker¹

2004

IEEJ Trans.EIS

View full text Add to dashboard Cite

Previous studies have demonstrated superior performance of artificial neural network (ANN) based forex forecasting models over traditional regression models. This paper applies support vector machines to build a forecasting model from the historical data using six simple technical indicators and presents a comparison with an ANN based model trained by scaled conjugate gradient (SCG) learning algorithm. The models are evaluated and compared on the basis of five commonly used performance metrics that measure closeness of prediction as well as correctness in directional change. Forecasting results of six different currencies against Australian dollar reveal superior performance of SVM model using simple linear kernel over ANN-SCG model in terms of all the evaluation metrics. The effect of SVM parameter selection on prediction performance is also investigated and analyzed.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Simulation Results and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Support Vector Machine to Forex Monitoring

Sarker¹

2004

IEEJ Trans.EIS

View full text Add to dashboard Cite

show abstract

“…Indeed, Yao et al have proposed an overview of forex technical forecasting [45], and Kamruzzaman et al have shown that support vector machines (SVMs) and NNs could be used for predicting foreign currency exchange rates, respectively [18] [19].…”

Section: A Emh Randomness and Predictabilitymentioning

confidence: 99%

Case based reasoning approach for transaction outcomes prediction on currency markets

Wang

Sýkora

Archer

et al. 2009

2009 3rd International Workshop on Soft Computing Applications

View full text Add to dashboard Cite

“…Em particular, RNAs foram aplicadas para previsão de taxas de câmbio em [79][80][81][82][83][84], todos com algum grau de sucesso, porém nenhum deles com resultados fortes o suficiente para ser apontado como uma solução definitiva para o problema.…”

Section: Experimentos De Previsão De Taxas De Câmbiounclassified

Estimação De Redes Neurais Artificiais Através Do Método Generalizado Dos Momentos

CUNHA¹

View full text Add to dashboard Cite

Cunha, João Marco Braga da; Aguiar, Alexandre Street de (Advisor). Estimating Artificial Neural Networks with Generalized Method of Moments. Rio de Janeiro, 2015. 90p. PhD Thesis -Departmento de Engenharia Elétrica, Pontifícia Universidade Católica do Rio de Janeiro.Artificial Neural Networks (ANN) started being developed in the decade of 1940. However, it was during the 1980's that the ANNs became relevant, pushed by the popularization and increasing power of computers. Also in the 1980's, there were two other two other academic events closely related to the present work: (i) a large increase of interest in nonlinear models from econometricians, culminating in the econometric approaches for ANN by the end of that decade; and (ii) the introduction of the Generalized Method of Moments (GMM) for parameter estimation in 1982. In econometric approaches for ANNs, the estimation by Quasi Maximum Likelihood (QML) always prevailed. Despite its good asymptotic properties, QML is very prone to an issue in finite sample estimations, known as overfitting. This thesis expands the state of the art in econometric approaches for ANNs by presenting an alternative to QML estimation that keeps its good asymptotic properties and has reduced leaning to overfitting. The presented approach relies on GMM estimation. As a byproduct, GMM estimation allows the use of the so-called J Test to verify the existence of neglected nonlinearity. The performed Monte Carlo studies indicate that the estimates from GMM are more accurate than those generated by QML in situations with high noise, especially in small samples. This result supports the hypothesis that GMM is susceptible to overfitting. Exchange rate forecasting experiments reinforced these findings. A second Monte Carlo study revealed satisfactory finite sample properties of the J Test applied to the neglected nonlinearity, compared with a reference test widely known and used. Overall, the results indicated that the estimation by GMM is a better alternative, especially for data with high noise level. * KeywordsArtificial Neural Networks; Multilayer Perceptron; Overfitting; Neglected Nonlinearity; Quasi Maximum Likelihood; Generalized Method of Moments; J-Test; Global Optimization. Uma série de outros tipos de RNAs foram desenvolvidos desde então. Muitas delas possuem uma estrutura desenhada para um propósito específico e, consequentemente, são treinadas através de algoritmos próprios. Apenas como ordem de grandeza, o verbete da Wikipédia dedicado aos tipos de RNAs (em inglês) apresentava, em janeiro de 2015, sete tipos principais de RNAs (muitos dos quais com subtipos), além de uma categoria denominada "Other Types', com mais oito tipos aparentemente menos relevantes. Detalhes sobre a maioria destes tipos de RNAs podem ser encontrados no compêndio [1].Apesar da diversidade de algoritmos de aprendizagem desenvolvidos existentes, todos podem ser classificados dentro de três paradigmas básicos. Na chamada aprendizagem supervisionada, há um conjunto estático de dados e, para cada veto...

show abstract

Forecasting of currency exchange rates using ANN: a case study

Cited by 99 publications

References 18 publications

Application of Support Vector Machine to Forex Monitoring

Application of Support Vector Machine to Forex Monitoring

Case based reasoning approach for transaction outcomes prediction on currency markets

Estimação De Redes Neurais Artificiais Através Do Método Generalizado Dos Momentos

Contact Info

Product

Resources

About