A Trainable Reconciliation Method for Hierarchical Time-Series

In numerous applications, it is required to produce forecasts for multiple time-series at different hierarchy levels. An obvious example is given by the supply chain in which demand forecasting may be needed at a store, city, or country level. The independent forecasts typically do not add up properly because of the hierarchical constraints, so a reconciliation step is needed. In this paper, we propose a new general, flexible, and easy-to-implement reconciliation strategy based on an encoder-decoder neural network. By testing our method on four realworld datasets, we show that it can consistently reach or surpass the performance of existing methods in the reconciliation setting.

[1]  Veronica Piccialli,et al.  A machine learning approach for forecasting hierarchical time series , 2021, Expert Syst. Appl..

[2]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[3]  José Manuel Benítez,et al.  On the use of cross-validation for time series predictor evaluation , 2012, Inf. Sci..

[4]  Federico Vaggi,et al.  A Self-supervised Approach to Hierarchical Forecasting with Applications to Groupwise Synthetic Controls , 2019, ArXiv.

[5]  Jeffrey Sohl,et al.  Disaggregation methods to expedite product line forecasting , 1990 .

[6]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[7]  Valentin Flunkert,et al.  DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks , 2017, International Journal of Forecasting.

[8]  Rob J. Hyndman,et al.  A note on the validity of cross-validation for evaluating autoregressive time series prediction , 2018, Comput. Stat. Data Anal..

[9]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[10]  Rob J. Hyndman,et al.  Optimal combination forecasts for hierarchical time series , 2011, Comput. Stat. Data Anal..

[11]  George Athanasopoulos,et al.  Hierarchical forecasts for Australian domestic tourism , 2009 .

[12]  George Athanasopoulos,et al.  hts : An R Package for Forecasting Hierarchical or Grouped Time Series , 2013 .

[13]  J. Sola,et al.  Importance of input data normalization for the application of neural networks to complex industrial problems , 1997 .

[14]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[15]  Rob J. Hyndman,et al.  Optimal Forecast Reconciliation for Hierarchical and Grouped Time Series Through Trace Minimization , 2018, Journal of the American Statistical Association.

[16]  Frank Hutter,et al.  Decoupled Weight Decay Regularization , 2017, ICLR.

[17]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).