ProbPNN: Enhancing Deep Probabilistic Forecasting with Statistical Information
This work addresses a specific bottleneck in probabilistic forecasting for applications like business and traffic planning, offering an incremental improvement by integrating statistical components into neural networks.
The paper tackles the problem of probabilistic forecasting for time series with calendar-driven periodicities by introducing ProbPNN, a deep learning method that explicitly incorporates statistical information from these periodicities, resulting in improved forecast performance and lower computational costs compared to other deep learning methods.
Probabilistic forecasts are essential for various downstream applications such as business development, traffic planning, and electrical grid balancing. Many of these probabilistic forecasts are performed on time series data that contain calendar-driven periodicities. However, existing probabilistic forecasting methods do not explicitly take these periodicities into account. Therefore, in the present paper, we introduce a deep learning-based method that considers these calendar-driven periodicities explicitly. The present paper, thus, has a twofold contribution: First, we apply statistical methods that use calendar-driven prior knowledge to create rolling statistics and combine them with neural networks to provide better probabilistic forecasts. Second, we benchmark ProbPNN with state-of-the-art benchmarks by comparing the achieved normalised continuous ranked probability score (nCRPS) and normalised Pinball Loss (nPL) on two data sets containing in total more than 1000 time series. The results of the benchmarks show that using statistical forecasting components improves the probabilistic forecast performance and that ProbPNN outperforms other deep learning forecasting methods whilst requiring less computation costs.