Rights statement: The final, definitive version of this article has been published in the Journal, Expert Systems with Applications ? (?), 2014, © ELSEVIER.
Submitted manuscript, 268 KB, PDF document
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Neural network ensemble operators for time series forecasting
AU - Kourentzes, Nikos
AU - Barrow, Devon
AU - Crone, Sven
N1 - The final, definitive version of this article has been published in the Journal, Expert Systems with Applications 41 (9), 2014, © ELSEVIER.
PY - 2014/7
Y1 - 2014/7
N2 - The combination of forecasts resulting from an ensemble of neural networks has been shown to outperform the use of a single ``best'' network model. This is supported by an extensive body of literature, which shows that combining generally leads to improvements in forecasting accuracy and robustness, and that using the mean operator often outperforms more complex methods of combining forecasts. This paper proposes a mode ensemble operator based on kernel density estimation, which unlike the mean operator is insensitive to outliers and deviations from normality, and unlike the median operator does not require symmetric distributions. The three operators are compared empirically and the proposed mode ensemble operator is found to produce the most accurate forecasts, followed by the median, while the mean has relatively poor performance. The findings suggest that the mode operator should be considered as an alternative to the mean and median operators in forecasting applications. Experiments indicate that mode ensembles are useful in automating neural network models across a large number of time series, overcoming issues of uncertainty associated with data sampling, the stochasticity of neural network training and the distribution of the forecasts.
AB - The combination of forecasts resulting from an ensemble of neural networks has been shown to outperform the use of a single ``best'' network model. This is supported by an extensive body of literature, which shows that combining generally leads to improvements in forecasting accuracy and robustness, and that using the mean operator often outperforms more complex methods of combining forecasts. This paper proposes a mode ensemble operator based on kernel density estimation, which unlike the mean operator is insensitive to outliers and deviations from normality, and unlike the median operator does not require symmetric distributions. The three operators are compared empirically and the proposed mode ensemble operator is found to produce the most accurate forecasts, followed by the median, while the mean has relatively poor performance. The findings suggest that the mode operator should be considered as an alternative to the mean and median operators in forecasting applications. Experiments indicate that mode ensembles are useful in automating neural network models across a large number of time series, overcoming issues of uncertainty associated with data sampling, the stochasticity of neural network training and the distribution of the forecasts.
KW - Time Series
KW - Forecasting
KW - Ensembles
KW - Combination
KW - Mode Estimation
KW - Kernel Density Estimation
KW - Neural Networks
KW - Mean
KW - Median
U2 - 10.1016/j.eswa.2013.12.011
DO - 10.1016/j.eswa.2013.12.011
M3 - Journal article
VL - 41
SP - 4235
EP - 4244
JO - Expert Systems with Applications
JF - Expert Systems with Applications
SN - 0957-4174
IS - 9
ER -