Hierarchically Coherent Multivariate Mixture Networks
This work addresses forecasting consistency across aggregation levels for applications like product and geographical groupings, representing an incremental advance.
The paper tackles the problem of probabilistic coherent forecasting for hierarchical time series data, achieving a 13.2% average accuracy improvement over state-of-the-art baselines.
Large collections of time series data are often organized into hierarchies with different levels of aggregation; examples include product and geographical groupings. Probabilistic coherent forecasting is tasked to produce forecasts consistent across levels of aggregation. In this study, we propose to augment neural forecasting architectures with a coherent multivariate mixture output. We optimize the networks with a composite likelihood objective, allowing us to capture time series' relationships while maintaining high computational efficiency. Our approach demonstrates 13.2% average accuracy improvements on most datasets compared to state-of-the-art baselines. We conduct ablation studies of the framework components and provide theoretical foundations for them. To assist related work, the code is available at this https://github.com/Nixtla/neuralforecast.