Nonlinear Forecasting with Many Predictors Using Kernel Ridge Regression

Exterkate, Peter; Groenen, Patrick J. F.; Heij, Christiaan; Dijk, Dick J. C. van

doi:10.2139/ssrn.1738192

Cited by 14 publications

(13 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is very hard to improve on standard PCA forecasts for these series, a finding that was also documented by Exterkate et al (2011). Nevertheless, our result that sparse modelling leads to better forecasts for annual growth rates also applies here.…”

Section: Forecasting Resultssupporting

confidence: 77%

Sparse and Robust Factor Modelling

Croux

Exterkate

2011

SSRN Journal

Self Cite

View full text Add to dashboard Cite

Section: Forecasting Resultssupporting

confidence: 77%

Sparse and Robust Factor Modelling

Croux

Exterkate

2011

SSRN Journal

Self Cite

View full text Add to dashboard Cite

“…The DM test is a classical forecast evaluation method, which is proposed by Diebold and Mariano (1995). It is a popular method for evaluating the predictive power of models (see, e.g., Andersen et al, 2011;Exterkate, Groenen, Heij, & van Dijk, 2016). The DM test statistic can be expressed as…”

Section: Forecast Evaluation Methodsmentioning

confidence: 99%

Structural breaks and volatility forecasting in the copper futures market

Gong

Lin

2017

Journal of Futures Markets

142

View full text Add to dashboard Cite

This paper examines whether structural breaks contain incremental information for forecasting the volatility of copper futures. Considering structural breaks in volatility, we develop four heterogeneous autoregressive (HAR) models based on classical or latest HAR‐type models. Subsequently, we apply these models to forecast volatility in the copper futures market. The empirical results reveal that our models exhibit better in‐sample and out‐of‐sample performances than classical or latest HAR‐type models. This suggests that structural breaks contain incremental prediction information for the volatility of copper futures. More importantly, we argue that considering structural breaks can improve the performances of most of existing HAR‐type models. Highlights There are many structural break points in return volatility of the copper futures. We propose 12 new heterogeneous autoregressive models. Our models outperform the existing heterogeneous autoregressive models. Structural breaks contain additional ex ante information for volatility forecasting. The ex ante information is obvious in forecasting mid‐ and long‐term volatilities.

show abstract

“…As an example, Exterkate et al (2011) derive the following expression for ϕ (x) for the Gaussian kernel: it contains, for each combination of nonnegative degrees…”

Section: Some Popular Kernel Functionsmentioning

confidence: 99%

“…A typical application is classification, such as optical recognition of scanned handwritten characters . Recently, Exterkate et al (2011) use this technique in a macroeconomic forecasting application and they report an increase in forecast accuracy, compared to traditional linear methods.…”

Section: Introductionmentioning

confidence: 99%

Modelling Issues in Kernel Ridge Regression

Exterkate

2011

SSRN Journal

Self Cite

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in AbstractKernel ridge regression is gaining popularity as a data-rich nonlinear forecasting tool, which is applicable in many different contexts. This paper investigates the influence of the choice of kernel and the setting of tuning parameters on forecast accuracy. We review several popular kernels, including polynomial kernels, the Gaussian kernel, and the Sinc kernel. We interpret the latter two kernels in terms of their smoothing properties, and we relate the tuning parameters associated to all these kernels to smoothness measures of the prediction function and to the signal-to-noise ratio. Based on these interpretations, we provide guidelines for selecting the tuning parameters from small grids using cross-validation. A Monte Carlo study confirms the practical usefulness of these rules of thumb. Finally, the flexible and smooth functional forms provided by the Gaussian and Sinc kernels makes them widely applicable, and we recommend their use instead of the popular polynomial kernels in general settings, in which no information on the data-generating process is available.

show abstract

Nonlinear Forecasting with Many Predictors Using Kernel Ridge Regression

Cited by 14 publications

References 36 publications

Sparse and Robust Factor Modelling

Sparse and Robust Factor Modelling

Structural breaks and volatility forecasting in the copper futures market

Modelling Issues in Kernel Ridge Regression

Contact Info

Product

Resources

About