SPADE-S: A Sparsity-Robust Foundational Forecaster

• URL: http://arxiv.org/abs/2507.21155v2
• Date: Wed, 06 Aug 2025 00:19:32 GMT
• Title: SPADE-S: A Sparsity-Robust Foundational Forecaster
• Authors: Malcolm Wolff, Matthew Li, Ravi Kiran Selvam, Hanjing Zhu, Kin G. Olivares, Ruijun Ma, Abhinav Katoch, Shankar Ramasubramanian, Mengfei Cao, Roberto Bandarra, Rahul Gopalsamy, Stefania La Vattiata, Sitan Yang, Michael W. Mahoney,
• Abstract summary: SPADE-S is a robust forecasting architecture that significantly reduces magnitude- and sparsity-based systematic biases and improves overall prediction accuracy.<n>We show that SPADE-S can improve forecast accuracy by up to 15% depending on the quantile forecast and magnitude of the series.
• Score: 31.818058575031888
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite significant advancements in time series forecasting, accurate modeling of time series with strong heterogeneity in magnitude and/or sparsity patterns remains challenging for state-of-the-art deep learning architectures. We identify several factors that lead existing models to systematically underperform on low-magnitude and sparse time series, including loss functions with implicit biases toward high-magnitude series, training-time sampling methods, and limitations of time series encoding methods. SPADE-S is a robust forecasting architecture that significantly reduces magnitude- and sparsity-based systematic biases and improves overall prediction accuracy. Empirical results demonstrate that SPADE-S outperforms existing state-of-the-art approaches across a diverse set of use cases in demand forecasting. In particular, we show that, depending on the quantile forecast and magnitude of the series, SPADE-S can improve forecast accuracy by up to 15%. This results in P90 overall forecast accuracy gains of 2.21%, 6.58%, and 4.28%, and P50 forecast accuracy gains of 0.92%, 0.77%, and 1.95%, respectively, for each of three distinct datasets, ranging from 3 million to 700 million series, from a large online retailer.

Related papers

• FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale [91.84761739154366]
  FourCastNet 3 advances global weather modeling by implementing a scalable, geometric machine learning (ML) approach to probabilistic ensemble forecasting.<n>FourCastNet 3 delivers forecasting accuracy that surpasses leading conventional ensemble models and rivals the best diffusion-based methods.<n>Its computational efficiency, medium-range probabilistic skill, spectral fidelity, and rollout stability at subseasonal timescales make it a strong candidate for improving meteorological forecasting and early warning systems through large ensemble predictions.
  arXiv  Detail & Related papers  (2025-07-16T11:22:18Z)
• RainPro-8: An Efficient Deep Learning Model to Estimate Rainfall Probabilities Over 8 Hours [4.726419619132143]
  We present a deep learning model for high-resolution probabilistic precipitation forecasting over an 8-hour horizon in Europe.<n>Our model efficiently integrates multiple data sources - including radar, satellite, and physics-based numerical weather prediction (NWP) - while capturing long-range interactions.
  arXiv  Detail & Related papers  (2025-05-15T13:22:20Z)
• Accurate and Reliable Predictions with Mutual-Transport Ensemble [46.368395985214875]
  We propose a co-trained auxiliary model and adaptively regularizes the cross-entropy loss using Kullback-Leibler (KL) We show that MTE can simultaneously enhance both accuracy and uncertainty calibration. For example, on the CIFAR-100 dataset, our MTE method on ResNet34/50 achieved significant improvements compared to previous state-of-the-art method.
  arXiv  Detail & Related papers  (2024-05-30T03:15:59Z)
• ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast [57.6987191099507]
  We introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast. We also introduce ExBooster, which captures the uncertainty in prediction outcomes by employing multiple random samples. Our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.
  arXiv  Detail & Related papers  (2024-02-02T10:34:13Z)
• GenCast: Diffusion-based ensemble forecasting for medium-range weather [10.845679586464026]
  We introduce GenCast, a probabilistic weather model with greater skill and speed than the top operational medium-range weather forecast in the world. GenCast generates an ensemble of 15-day global forecasts, at 12-hour steps and 0.25 degree latitude-longitude, for over 80 surface and atmospheric variables in 8 minutes. It has greater skill than ENS on 97.4% of 1320 targets we evaluated, and better predicts extreme weather, tropical cyclones, and wind power production.
  arXiv  Detail & Related papers  (2023-12-25T19:30:06Z)
• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2023-10-17T20:30:16Z)
• PostRainBench: A comprehensive benchmark and a new model for precipitation forecasting [14.855615256498]
  We focus on the Numerical Weather Prediction (NWP) post-processing based precipitation forecasting task. We introduce the textbfPostRainBench, a comprehensive multi-variable NWP post-processing benchmark, and textbfCAMT, a simple yet effective Channel Attention Enhanced Multi-task Learning framework. Our model is the first deep learning-based method to outperform NWP approaches in heavy rain conditions.
  arXiv  Detail & Related papers  (2023-10-04T09:27:39Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• Learning Sample Difficulty from Pre-trained Models for Reliable Prediction [55.77136037458667]
  We propose to utilize large-scale pre-trained models to guide downstream model training with sample difficulty-aware entropy regularization. We simultaneously improve accuracy and uncertainty calibration across challenging benchmarks.
  arXiv  Detail & Related papers  (2023-04-20T07:29:23Z)
• FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead [93.67314652898547]
  We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI) FengWu is able to accurately reproduce the atmospheric dynamics and predict the future land and atmosphere states at 37 vertical levels on a 0.25deg latitude-longitude resolution. The results suggest that FengWu can significantly improve the forecast skill and extend the skillful global medium-range weather forecast out to 10.75 days lead.
  arXiv  Detail & Related papers  (2023-04-06T09:16:39Z)
• A Machine Learning Outlook: Post-processing of Global Medium-range Forecasts [0.0]
  Post-processing typically takes the outputs of a Numerical Weather Prediction (NWP) model and applies linear statistical techniques. We show that we can achieve accuracy improvements of up to 12% (RMSE) in a field such as temperature at 850hPa for a 7 day forecast. We discuss the challenges of using standard metrics such as root mean squared error (RMSE) or anomaly correlation coefficient (ACC)
  arXiv  Detail & Related papers  (2023-03-28T20:48:01Z)
• Beyond S-curves: Recurrent Neural Networks for Technology Forecasting [60.82125150951035]
  We develop an autencoder approach that employs recent advances in machine learning and time series forecasting. S-curves forecasts largely exhibit a mean average percentage error (MAPE) comparable to a simple ARIMA baseline. Our autoencoder approach improves the MAPE by 13.5% on average over the second-best result.
  arXiv  Detail & Related papers  (2022-11-28T14:16:22Z)
• DMIDAS: Deep Mixed Data Sampling Regression for Long Multi-Horizon Time Series Forecasting [13.458489651961106]
  We develop a method to predict long-term energy prices using high-frequency healthcare and electricity price data. We improve the prediction accuracy by 5% over state-of-the-art models, reducing the number of parameters of NBEATS by nearly 70%.
  arXiv  Detail & Related papers  (2021-06-07T22:36:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.