Abstract:We present the Hierarchical Mixture Networks (HINT), a model family for efficient and accurate coherent forecasting. We specialize the networks on the task via a multivariate mixture optimized with composite likelihood and made coherent via bootstrap reconciliation. Additionally, we robustify the networks to stark time series scale variations, incorporating normalized feature extraction and recomposition of output scales within their architecture. We demonstrate 8% sCRPS improved accuracy across five datasets compared to the existing state-of-the-art. We conduct ablation studies on our model's components and extensively investigate the theoretical properties of the multivariate mixture. HINT's code is available at this https://github.com/Nixtla/neuralforecast.
Abstract:Large collections of time series data are commonly organized into cross-sectional structures with different levels of aggregation; examples include product and geographical groupings. A necessary condition for coherent decision-making and planning, with such data sets, is for the dis-aggregated series' forecasts to add up exactly to the aggregated series forecasts, which motivates the creation of novel hierarchical forecasting algorithms. The growing interest of the Machine Learning community in cross-sectional hierarchical forecasting systems states that we are in a propitious moment to ensure that scientific endeavors are grounded on sound baselines. For this reason, we put forward the HierarchicalForecast library, which contains preprocessed publicly available datasets, evaluation metrics, and a compiled set of statistical baseline models. Our Python-based framework aims to bridge the gap between statistical, econometric modeling, and Machine Learning forecasting research. Code and documentation are available in https://github.com/Nixtla/hierarchicalforecast.