Adaptive Evolutionary Neural Networks for Forecasting and Trading without a Data‐Snooping Bias

In this paper, we present two neural‐network‐based techniques: an adaptive evolutionary multilayer perceptron (aDEMLP) and an adaptive evolutionary wavelet neural network (aDEWNN). The two models are applied to the task of forecasting and trading the SPDR Dow Jones Industrial Average (DIA), the iShares NYSE Composite Index Fund (NYC) and the SPDR S&P 500 (SPY) exchange‐traded funds (ETFs). We benchmark their performance against two traditional MLP and WNN architectures, a smooth transition autoregressive model (STAR), a moving average convergence/divergence model (MACD) and a random walk model. We show that the proposed architectures present superior forecasting and trading performance compared to the benchmarks and are free from the limitations of the traditional neural networks such as the data‐snooping bias and the time‐consuming and biased processes involved in optimizing their parameters. Copyright © 2015 John Wiley & Sons, Ltd.     

Modelling and Trading the English and German Stock Markets with Novelty Optimization Techniques

The motivation for this paper was the introduction of novel short‐term models to trade the FTSE 100 and DAX 30 exchange‐traded funds (ETF) indices. There are major contributions in this paper which include the introduction of an input selection criterion when utilizing an expansive universe of inputs, a hybrid combination of partial swarm optimizer (PSO) with radial basis function (RBF) neural networks, the application of a PSO algorithm to a traditional autoregressive moving model (ARMA), the application of a PSO algorithm to a higher‐order neural network and, finally, the introduction of a multi‐objective algorithm to optimize statistical and trading performance when trading an index. All the machine learning‐based methodologies and the conventional models are adapted and optimized to model the index. A PSO algorithm is used to optimize the weights in a traditional RBF neural network, in a higher‐order neural network (HONN) and the AR and MA terms of an ARMA model. In terms of checking the statistical and empirical accuracy of the novel models, we benchmark them with a traditional HONN, with an ARMA, with a moving average convergence/divergence model (MACD) and with a naïve strategy. More specifically, the trading and statistical performance of all models is investigated in a forecast simulation of the FTSE 100 and DAX 30 ETF time series over the period January 2004 to December 2015 using the last 3 years for out‐of‐sample testing. Finally, the empirical and statistical results indicate that the PSO‐RBF model outperforms all other examined models in terms of trading accuracy and profitability, even with mixed inputs and with only autoregressive inputs. Copyright © 2016 John Wiley & Sons, Ltd.     

Forecasting volatility with support vector machine‐based GARCH model

Recently, support vector machine (SVM), a novel artificial neural network (ANN), has been successfully used for financial forecasting. This paper deals with the application of SVM in volatility forecasting under the GARCH framework, the performance of which is compared with simple moving average, standard GARCH, nonlinear EGARCH and traditional ANN‐GARCH models by using two evaluation measures and robust Diebold–Mariano tests. The real data used in this study are daily GBP exchange rates and NYSE composite index. Empirical results from both simulation and real data reveal that, under a recursive forecasting scheme, SVM‐GARCH models significantly outperform the competing models in most situations of one‐period‐ahead volatility forecasting, which confirms the theoretical advantage of SVM. The standard GARCH model also performs well in the case of normality and large sample size, while EGARCH model is good at forecasting volatility under the high skewed distribution. The sensitivity analysis to choose SVM parameters and cross‐validation to determine the stopping point of the recurrent SVM procedure are also examined in this study. Copyright © 2009 John Wiley & Sons, Ltd.     

Predictive likelihood for coherent forecasting of count time series

A new forecasting method based on the concept of the profile predictive likelihood function is proposed for discrete‐valued processes. In particular, generalized autoregressive moving average (GARMA) models for Poisson distributed data are explored in detail. Highest density regions are used to construct forecasting regions. The proposed forecast estimates and regions are coherent. Large‐sample results are derived for the forecasting distribution. Numerical studies using simulations and two real data sets are used to establish the performance of the proposed forecasting method. Robustness of the proposed method to possible misspecifications in the model is also studied.     

Forecasting carbon price using a multi-objective least squares support vector machine with mixture kernels

For improving forecasting accuracy and trading performance, this paper proposes a new multi-objective least squares support vector machine with mixture kernels to forecast asset prices. First, a mixture kernel function is introduced into taking full use of global and local kernel functions, which is adaptively determined following a data-driven procedure. Second, a multi-objective fitness function is proposed by incorporating level forecasting and trading performance, and particle swarm optimization is used to synchronously search the optimal model selections of least squares support vector machine with mixture kernels. Taking CO₂ assets as examples, the results obtained show that compared with the popular models, the proposed model can achieve higher forecasting accuracy and higher trading performance. The advantages of the mixture kernel function and the multi-objective fitness function can improve the forecasting ability of the asset price. The findings also show that the models with a high-level forecasting accuracy cannot always have a high trading performance of asset price forecasting. In contrast, high directional forecasting usually means a high trading performance.     

Forecasting nonlinear time series with feed‐forward neural networks: a case study of Canadian lynx data

The forecasting capabilities of feed‐forward neural network (FFNN) models are compared to those of other competing time series models by carrying out forecasting experiments. As demonstrated by the detailed forecasting results for the Canadian lynx data set, FFNN models perform very well, especially when the series contains nonlinear and non‐Gaussian characteristics. To compare the forecasting accuracy of a FFNN model with an alternative model, Pitman's test is employed to ascertain if one model forecasts significantly better than another when generating one‐step‐ahead forecasts. Moreover, the residual‐fit spread plot is utilized in a novel fashion in this paper to compare visually out‐of‐sample forecasts of two alternative forecasting models. Finally, forecasting findings on the lynx data are used to explain under what conditions one would expect FFNN models to furnish reliable and accurate forecasts. Copyright © 2005 John Wiley & Sons, Ltd.     

A non‐Gaussian generalization of the Airline model for robust seasonal adjustment

In their seminal book Time Series Analysis: Forecasting and Control, Box and Jenkins (1976) introduce the Airline model, which is still routinely used for the modelling of economic seasonal time series. The Airline model is for a differenced time series (in levels and seasons) and constitutes a linear moving average of lagged Gaussian disturbances which depends on two coefficients and a fixed variance. In this paper a novel approach to seasonal adjustment is developed that is based on the Airline model and that accounts for outliers and breaks in time series. For this purpose we consider the canonical representation of the Airline model. It takes the model as a sum of trend, seasonal and irregular (unobserved) components which are uniquely identified as a result of the canonical decomposition. The resulting unobserved components time series model is extended by components that allow for outliers and breaks. When all components depend on Gaussian disturbances, the model can be cast in state space form and the Kalman filter can compute the exact log‐likelihood function. Related filtering and smoothing algorithms can be used to compute minimum mean squared error estimates of the unobserved components. However, the outlier and break components typically rely on heavy‐tailed densities such as the t or the mixture of normals. For this class of non‐Gaussian models, Monte Carlo simulation techniques will be used for estimation, signal extraction and seasonal adjustment. This robust approach to seasonal adjustment allows outliers to be accounted for, while keeping the underlying structures that are currently used to aid reporting of economic time series data. Copyright © 2006 John Wiley & Sons, Ltd.     

Term premia and the maturity composition of the Federal debt: new evidence from the term structure of interest rates

This paper models bond term premia empirically in terms of the maturity composition of the federal debt and other observable economic variables in a time‐varying framework with potential regime shifts. We present regression and out‐of sample forecasting results demonstrating that information on the age composition of the Federal debt is useful for forecasting term premia. We show that the multiprocess mixture model, a multi‐state time‐varying parameter model, outperforms the commonly used GARCH model in out‐of‐sample forecasts of term premia. The results underscore the importance of modelling term premia, as a function of economic variables rather than just as a function of asset covariances as in the conditional heteroscedasticity models. Copyright © 2001 John Wiley & Sons, Ltd.     

Adaptive learning from model space

Dynamic model averaging (DMA) is used extensively for the purpose of economic forecasting. This study extends the framework of DMA by introducing adaptive learning from model space. In the conventional DMA framework all models are estimated independently and hence the information of the other models is left unexploited. In order to exploit the information in the estimation of the individual time‐varying parameter models, this paper proposes not only to average over the forecasts but, in addition, also to dynamically average over the time‐varying parameters. This is done by approximating the mixture of individual posteriors with a single posterior, which is then used in the upcoming period as the prior for each of the individual models. The relevance of this extension is illustrated in three empirical examples involving forecasting US inflation, US consumption expenditures, and forecasting of five major US exchange rate returns. In all applications adaptive learning from model space delivers improvements in out‐of‐sample forecasting performance.     

Comparison of two non‐parametric models for daily traffic forecasting in Hong Kong

The most up‐to‐date annual average daily traffic (AADT) is always required for transport model development and calibration. However, the current‐year AADT data are not always available. The short‐term traffic flow forecasting models can be used to predict the traffic flows for the current year. In this paper, two non‐parametric models, non‐parametric regression (NPR) and Gaussian maximum likelihood (GML), are chosen for short‐term traffic forecasting based on historical data collected for the annual traffic census (ATC) in Hong Kong. These models are adapted as they are more flexible and efficient in forecasting the daily vehicular flows in the Hong Kong ATC core stations (in total of 87 stations). The daily vehicular flows predicted by these models are then used to calculate the AADT of the current year, 1999. The overall prediction and comparison results show that the NPR model produces better forecasts than the GML model using the ATC data in Hong Kong. Copyright © 2006 John Wiley _ Sons, Ltd.     

Assessing the forecasting accuracy of alternative nominal exchange rate models: the case of long memory

This paper presents an autoregressive fractionally integrated moving‐average (ARFIMA) model of nominal exchange rates and compares its forecasting capability with the monetary structural models and the random walk model. Monthly observations are used for Canada, France, Germany, Italy, Japan and the United Kingdom for the period of April 1973 through December 1998. The estimation method is Sowell's (1992) exact maximum likelihood estimation. The forecasting accuracy of the long‐memory model is formally compared to the random walk and the monetary models, using the recently developed Harvey, Leybourne and Newbold (1997) test statistics. The results show that the long‐memory model is more efficient than the random walk model in steps‐ahead forecasts beyond 1 month for most currencies and more efficient than the monetary models in multi‐step‐ahead forecasts. This new finding strongly suggests that the long‐memory model of nominal exchange rates be studied as a viable alternative to the conventional models. Copyright © 2006 John Wiley & Sons, Ltd.     

Modelling time series with season‐dependent autocorrelation structure

Time series with season‐dependent autocorrelation structure are commonly modelled using periodic autoregressive moving average (PARMA) processes. In most applications, the moving average terms are excluded for ease of estimation. We propose a new class of periodic unobserved component models (PUCM). Parameter estimates for PUCM are readily interpreted; the estimated coefficients correspond to variances of the measurement noise and of the error terms in unobserved components. We show that PUCM have correlation structure equivalent to that of a periodic integrated moving average (PIMA) process. Results from practical applications indicate that our models provide a natural framework for series with periodic autocorrelation structure both in terms of interpretability and forecasting accuracy. Copyright © 2008 John Wiley & Sons, Ltd.     

Daily volatility forecasts: reassessing the performance of GARCH models

Volatility plays a key role in asset and portfolio management and derivatives pricing. As such, accurate measures and good forecasts of volatility are crucial for the implementation and evaluation of asset and derivative pricing models in addition to trading and hedging strategies. However, whilst GARCH models are able to capture the observed clustering effect in asset price volatility in‐sample, they appear to provide relatively poor out‐of‐sample forecasts. Recent research has suggested that this relative failure of GARCH models arises not from a failure of the model but a failure to specify correctly the ‘true volatility’ measure against which forecasting performance is measured. It is argued that the standard approach of using ex post daily squared returns as the measure of ‘true volatility’ includes a large noisy component. An alternative measure for ‘true volatility’ has therefore been suggested, based upon the cumulative squared returns from intra‐day data. This paper implements that technique and reports that, in a dataset of 17 daily exchange rate series, the GARCH model outperforms smoothing and moving average techniques which have been previously identified as providing superior volatility forecasts. Copyright © 2004 John Wiley & Sons, Ltd.     

Long Memory of Financial Time Series and Hidden Markov Models with Time‐Varying Parameters

Hidden Markov models are often used to model daily returns and to infer the hidden state of financial markets. Previous studies have found that the estimated models change over time, but the implications of the time‐varying behavior have not been thoroughly examined. This paper presents an adaptive estimation approach that allows for the parameters of the estimated models to be time varying. It is shown that a two‐state Gaussian hidden Markov model with time‐varying parameters is able to reproduce the long memory of squared daily returns that was previously believed to be the most difficult fact to reproduce with a hidden Markov model. Capturing the time‐varying behavior of the parameters also leads to improved one‐step density forecasts. Finally, it is shown that the forecasting performance of the estimated models can be further improved using local smoothing to forecast the parameter variations. Copyright © 2016 John Wiley & Sons, Ltd.     

Neural network versus econometric models in forecasting inflation

Artificial neural network modelling has recently attracted much attention as a new technique for estimation and forecasting in economics and finance. The chief advantages of this new approach are that such models can usually find a solution for very complex problems, and that they are free from the assumption of linearity that is often adopted to make the traditional methods tractable. In this paper we compare the performance of Back‐Propagation Artificial Neural Network (BPN) models with the traditional econometric approaches to forecasting the inflation rate. Of the traditional econometric models we use a structural reduced‐form model, an ARIMA model, a vector autoregressive model, and a Bayesian vector autoregression model. We compare each econometric model with a hybrid BPN model which uses the same set of variables. Dynamic forecasts are compared for three different horizons: one, three and twelve months ahead. Root mean squared errors and mean absolute errors are used to compare quality of forecasts. The results show the hybrid BPN models are able to forecast as well as all the traditional econometric methods, and to outperform them in some cases. Copyright © 2000 John Wiley & Sons, Ltd.     

Forecasting and trading currency volatility: an application of recurrent neural regression and model combination

In this paper, we examine the use of non‐parametric Neural Network Regression (NNR) and Recurrent Neural Network (RNN) regression models for forecasting and trading currency volatility, with an application to the GBP/USD and USD/JPY exchange rates. Both the results of the NNR and RNN models are benchmarked against the simpler GARCH alternative and implied volatility. Two simple model combinations are also analysed. The intuitively appealing idea of developing a nonlinear nonparametric approach to forecast FX volatility, identify mispriced options and subsequently develop a trading strategy based upon this process is implemented for the first time on a comprehensive basis. Using daily data from December 1993 through April 1999, we develop alternative FX volatility forecasting models. These models are then tested out‐of‐sample over the period April 1999–May 2000, not only in terms of forecasting accuracy, but also in terms of trading efficiency: in order to do so, we apply a realistic volatility trading strategy using FX option straddles once mispriced options have been identified. Allowing for transaction costs, most trading strategies retained produce positive returns. RNN models appear as the best single modelling approach yet, somewhat surprisingly, model combination which has the best overall performance in terms of forecasting accuracy, fails to improve the RNN‐based volatility trading results. Another conclusion from our results is that, for the period and currencies considered, the currency option market was inefficient and/or the pricing formulae applied by market participants were inadequate. Copyright © 2002 John Wiley & Sons, Ltd.     

The geometric combination of Bayesian forecasting models

A nonlinear geometric combination of statistical models is proposed as an alternative approach to the usual linear combination or mixture. Contrary to the linear, the geometric model is closed under the regular exponential family of distributions, as we show. As a consequence, the distribution which results from the combination is unimodal and a single location parameter can be chosen for decision making. In the case of Student t‐distributions (of particular interest in forecasting) the geometric combination can be unimodal under a sufficient condition we have established. A comparative analysis between the geometric and linear combinations of predictive distributions from three Bayesian regression dynamic linear models, in a case of beer sales forecasting in Zimbabwe, shows the geometric model to consistently outperform its linear counterpart as well as its component models. Copyright © 2008 John Wiley & Sons, Ltd.     

Optimal forecast combination based on ensemble empirical mode decomposition for agricultural commodity futures prices

Improving the prediction accuracy of agricultural product futures prices is important for investors, agricultural producers, and policymakers. This is to evade risks and enable government departments to formulate appropriate agricultural regulations and policies. This study employs the ensemble empirical mode decomposition (EEMD) technique to decompose six different categories of agricultural futures prices. Subsequently, three models—support vector machine (SVM), neural network (NN), and autoregressive integrated moving average (ARIMA)—are used to predict the decomposition components. The final hybrid model is then constructed by comparing the prediction performance of the decomposition components. The predicting performance of the combination model is then compared with the benchmark individual models: SVM, NN, and ARIMA. Our main interest in this study is on short-term forecasting, and thus we only consider 1-day and 3-day forecast horizons. The results indicate that the prediction performance of the EEMD combined model is better than that of individual models, especially for the 3-day forecasting horizon. The study also concluded that the machine learning methods outperform the statistical methods in forecasting high-frequency volatile components. However, there is no obvious difference between individual models in predicting low-frequency components.     

Parameter Space Restrictions in State Space Models

The state space model is widely used to handle time series data driven by related latent processes in many fields. In this article, we suggest a framework to examine the relationship between state space models and autoregressive integrated moving average (ARIMA) models by examining the existence and positive‐definiteness conditions implied by auto‐covariance structures. This study covers broad types of state space models frequently used in previous studies. We also suggest a simple statistical test to check whether a certain state space model is appropriate for the specific data. For illustration, we apply the suggested procedure in the analysis of the United States real gross domestic product data. Copyright © 2011 John Wiley & Sons, Ltd.     

Comparison of forecasting performances: Does normalization and variance stabilization method beat GARCH(1,1)‐type models? Empirical evidence from the stock markets

In this paper, we present a comparison between the forecasting performances of the normalization and variance stabilization method (NoVaS) and the GARCH(1,1), EGARCH(1,1) and GJR‐GARCH(1,1) models. Hence the aim of this study is to compare the out‐of‐sample forecasting performances of the models used throughout the study and to show that the NoVaS method is better than GARCH(1,1)‐type models in the context of out‐of sample forecasting performance. We study the out‐of‐sample forecasting performances of GARCH(1,1)‐type models and NoVaS method based on generalized error distribution, unlike normal and Student's t‐distribution. Also, what makes the study different is the use of the return series, calculated logarithmically and arithmetically in terms of forecasting performance. For comparing the out‐of‐sample forecasting performances, we focused on different datasets, such as S&P 500, logarithmic and arithmetic B?ST 100 return series. The key result of our analysis is that the NoVaS method performs better out‐of‐sample forecasting performance than GARCH(1,1)‐type models. The result can offer useful guidance in model building for out‐of‐sample forecasting purposes, aimed at improving forecasting accuracy.