$\spadesuit$ SPADE $\spadesuit$ Split Peak Attention DEcomposition
Demand forecasting faces challenges induced by Peak Events (PEs) corresponding to special periods such as promotions and holidays. Peak events create significant spikes in demand followed by demand ramp down periods. Neural networks like MQCNN and MQT overreact to demand peaks by carrying over the elevated PE demand into subsequent Post-Peak-Event (PPE) periods, resulting in significantly over-biased forecasts. To tackle this challenge, we introduce a neural forecasting model called Split Peak Attention DEcomposition, SPADE. This model reduces the impact of PEs on subsequent forecasts by modeling forecasting as consisting of two separate tasks: one for PEs; and the other for the rest. Its architecture then uses masked convolution filters and a specialized Peak Attention module. We show SPADE's performance on a worldwide retail dataset with hundreds of millions of products. Our results reveal an overall PPE improvement of 4.5%, a 30% improvement for most affected forecasts after promotions and holidays, and an improvement in PE accuracy by 3.9%, relative to current production models.
Code (0)
등록된 구현이 없습니다.
Tasks
Demand ForecastingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SKDF: A Simple Knowledge Distillation Framework for Distilling Open-Vocabulary Knowledge to Open-world Object Detector
In this paper, we attempt to specialize the VLM model for OWOD tasks by distilling its open-world knowledge into a language-agnostic detector. Surprisingly, we observe that the combination of a simple \textbf{knowledge d…
Knowledge DistillationObjectobject-detectionObject Detection+2SPADE: Split-and-Delay Embeddings for Autoregressive High-Granularity Calorimeter Simulation
We introduce SPADE (SPlit And Delay Embeddings), an autoregressive transformer for sequences whose tokens carry multiple features. Rather than embedding these features jointly, SPADE embeds them independently. Delaying e…
SPADE: An Input-Adaptive Sparse Attention Engine for Fast Video Diffusion Models Inference
Video diffusion transformers (vDiTs) generate high quality but pay quadratic self-attention cost, making inference prohibitive at video-token scales. The challenge is input-adaptive sparsity: selecting critical Q/K/V tok…
Video GenerationSemantic Image Synthesis via Class-Adaptive Cross-Attention
In semantic image synthesis the state of the art is dominated by methods that use customized variants of the SPatially-Adaptive DE-normalization (SPADE) layers, which allow for good visual generation quality and editing …
Image GenerationSemantic SegmentationStyle TransferEfficient Long Sequence Modeling via State Space Augmented Transformer
Transformer models have achieved superior performance in various natural language processing tasks. However, the quadratic computational cost of the attention mechanism limits its practicality for long sequences. There a…
Computational EfficiencyDecoderLanguage ModelingLanguage Modelling+3