Probabilistic Forecast Reconciliation with Kullback-Leibler Divergence Regularization
This addresses the problem of improving probabilistic forecasting for hierarchical time series, offering a more flexible approach compared to fixed post-processing methods, though it appears incremental as it builds on existing reconciliation techniques.
The paper tackles the trade-off between accuracy and coherency in probabilistic forecast reconciliation by fusing prediction and reconciliation into a deep learning framework with Kullback-Leibler divergence regularization, showing advantages over existing methods on three hierarchical time series datasets.
As the popularity of hierarchical point forecast reconciliation methods increases, there is a growing interest in probabilistic forecast reconciliation. Many studies have utilized machine learning or deep learning techniques to implement probabilistic forecasting reconciliation and have made notable progress. However, these methods treat the reconciliation step as a fixed and hard post-processing step, leading to a trade-off between accuracy and coherency. In this paper, we propose a new approach for probabilistic forecast reconciliation. Unlike existing approaches, our proposed approach fuses the prediction step and reconciliation step into a deep learning framework, making the reconciliation step more flexible and soft by introducing the Kullback-Leibler divergence regularization term into the loss function. The approach is evaluated using three hierarchical time series datasets, which shows the advantages of our approach over other probabilistic forecast reconciliation methods.