Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2509.14113 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909793207189504 |
|---|---|
| author | Brusaferri, Alessandro Ramin, Danial Ballarino, Andrea |
| author_facet | Brusaferri, Alessandro Ramin, Danial Ballarino, Andrea |
| contents | While neural networks are achieving high predictive accuracy in multi-horizon probabilistic forecasting, understanding the underlying mechanisms that lead to feature-conditioned outputs remains a significant challenge for forecasters. In this work, we take a further step toward addressing this critical issue by introducing the Quantile Neural Basis Model, which incorporates the interpretability principles of Quantile Generalized Additive Models into an end-to-end neural network training framework. To this end, we leverage shared basis decomposition and weight factorization, complementing Neural Models for Location, Scale, and Shape by avoiding any parametric distributional assumptions. We validate our approach on day-ahead electricity price forecasting, achieving predictive performance comparable to distributional and quantile regression neural networks, while offering valuable insights into model behavior through the learned nonlinear mappings from input features to output predictions across the horizon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14113 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Distributional to Quantile Neural Basis Models: the case of Electricity Price Forecasting Brusaferri, Alessandro Ramin, Danial Ballarino, Andrea Machine Learning While neural networks are achieving high predictive accuracy in multi-horizon probabilistic forecasting, understanding the underlying mechanisms that lead to feature-conditioned outputs remains a significant challenge for forecasters. In this work, we take a further step toward addressing this critical issue by introducing the Quantile Neural Basis Model, which incorporates the interpretability principles of Quantile Generalized Additive Models into an end-to-end neural network training framework. To this end, we leverage shared basis decomposition and weight factorization, complementing Neural Models for Location, Scale, and Shape by avoiding any parametric distributional assumptions. We validate our approach on day-ahead electricity price forecasting, achieving predictive performance comparable to distributional and quantile regression neural networks, while offering valuable insights into model behavior through the learned nonlinear mappings from input features to output predictions across the horizon. |
| title | From Distributional to Quantile Neural Basis Models: the case of Electricity Price Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.14113 |