Much ado about nothing? Exchange rate forecasting: Neural networks vs. linear models using monthly and weekly data

Hann, Tae Horn; Steurer, Elmar

doi:10.1016/0925-2312(95)00137-9

Cited by 105 publications

(46 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They find the GRNN superior to all other models regarding forecasting accuracy. Hann and Steurer (1996), however, can only confirm a superior performance of Neural Networks for weekly data, but conclude that for their investigation of the USD/DEM exchange rate for data from January 1986 to October 1994 linear models and Neural Networks in the framework of error-correction models give almost the same results for monthly data. look into the impact of parameter settings of Neural Networks, applying them to the daily and weekly GBP/ USD exchange rate from the beginning of 1976 to the end of 1993.…”

Section: Literature Reviewmentioning

confidence: 79%

“…One method to determine the optimal number of hidden nodes was introduced by Le Cun et al (1990) and is known as Optimal Brain Damage: the idea is to start with an oversized model and to gradually prune redundant weights during the training procedure. Other methods are, for instance, the weight decay or weight elimination, using a penalty term for an increased network size that is added to the error function, a neural network information criterion assessing the trade-off between the accuracy of the approximation and the size of the network or a Principal Component Analysis (Hann and Steurer, 1996).…”

Section: Network Characteristicsmentioning

confidence: 99%

See 1 more Smart Citation

Currency trading in volatile markets: Did neural networks outperform for the EUR/USD during the financial crisis 2007–2009?

Dunis¹,

Laws²,

Schilling³

2012

J Deriv Hedge Funds

View full text Add to dashboard Cite

The motivation for this article is to check whether neural network models have remained a superior method for forecasting the EUR/USD exchange rate during the financial crisis of [2007][2008][2009]. Alternative neural network architectures (Multi-Layer Perceptron (MLP), Recurrent Neural Network and Higher Order Neural Network (HONN)) are benchmarked against a random walk and a traditional ARMA model, and evaluated in terms of statistical accuracy and through a trading simulation on daily data over the period from January 2000 to February 2009, the period from August 2007 to February 2009, providing the out-of-sample testing period. Transaction costs and a confirmation filter devised to reduce false signals and thus also reduce losses and transaction costs were also taken into consideration. It is shown that the HONN structure gives the overall best results on a simple trading simulation; however, for an advanced trading simulation with a confirmation filter, the MLP outperforms all other models on most performance measures. On the whole, the results show that neural networks are still able to produce forecasts that yield a positive return and are superior to those of linear and more traditional models, with respect to both trading performance and statistical accuracy, even under very volatile market conditions.

show abstract

Section: Literature Reviewmentioning

confidence: 79%

Section: Network Characteristicsmentioning

confidence: 99%

Currency trading in volatile markets: Did neural networks outperform for the EUR/USD during the financial crisis 2007–2009?

Dunis¹,

Laws²,

Schilling³

2012

J Deriv Hedge Funds

View full text Add to dashboard Cite

show abstract

“…The measurement U of THEIL which is also known as NMSE [8] determine the relationship between the model performances compared to a random walk model. U of THEIL is described by the equation: (6) if U of THEIL is equal to one, the tested model has the same performance of a random walk.…”

Section: U Of Theil or Nmse -Normalized Mean Square Errormentioning

confidence: 99%

Financial time series prediction using exogenous series and combined neural networks

Neto

Calvalcanti

Ren

2009

2009 International Joint Conference on Neural Networks

View full text Add to dashboard Cite

Abstract-Time series forecasting have been a subject of interest in several different areas of research such as: meteorology, demography, health, computer and finance. Since it can be applied to various practical problems in real world, techniques to predict time series have been a topic of increasing research activities, especially in the financial sector that has a great interest in the forecast of the stock market. In this article, we are interested in the forecast of the time series related to the Brazilian oil company, Petrobras (PETR4). A methodology based on information obtained from exogenous series was used in combination with a neural network to predict the PETR4 stock series. Exogenous series were selected by analyzing the correlation between the series with the Petrobras stocks series. In this way, the prediction was obtained by not just using the previous values of the series but also by using information external to the PETR4 series. The values of the selected series were used as features for a prediction stage based on combined neural networks. To evaluate the performance of the system classical measurements were used, however we also introduce a new performance index called Sum of the Losses and Gains (SLG).

show abstract

“…Thus, a way to evaluate the model regarding a random walk model is using the Normalized Mean Squared Error (NMSE) or U of Theil Statistic (THEIL) [70], which associates the model performance with a random walk model, and given by (63) where, if the THEIL is equal to 1, the predictor has the same performance than a random model. If the THEIL is greater than 1, then the predictor has a performance worse than a random walk model, and if the THEIL is less than 1, the predictor is better than a random walk model.…”

Section: Performance Metricsmentioning

confidence: 99%

Morphological-Rank-Linear Models for Financial Time Series Forecasting

Araújo¹,

Melo²,

Oliveira³

et al. 2010

New Achievements in Evolutionary Computation

View full text Add to dashboard Cite

Much ado about nothing? Exchange rate forecasting: Neural networks vs. linear models using monthly and weekly data

Cited by 105 publications

References 14 publications

Currency trading in volatile markets: Did neural networks outperform for the EUR/USD during the financial crisis 2007–2009?

Currency trading in volatile markets: Did neural networks outperform for the EUR/USD during the financial crisis 2007–2009?

Financial time series prediction using exogenous series and combined neural networks

Morphological-Rank-Linear Models for Financial Time Series Forecasting

Contact Info

Product

Resources

About