Unverified50% confidenceConceptExact time
WAPE is a commonly used evaluation metric in demand forecasting, calculated as the sum of absolute errors across all samples divided by the sum of actual values and then multiplied by 100%; compared with MAPE it is more robust for low-sales or zero-sales items, and a WAPE below 30% is generally considered a good level.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn the M5 Walmart dataset, the EventHorizon demand forecasting model achieved a WAPE of 31.03%, while the baseline model's WAPE was 44.4%, achieving roughly a 30% error reduction relative to the baseline.67% similarUnverifiedMonitoring information indicates that a price adjustment has occurred for Wafer-related models.61% similarUnverifiedUsing LoRA can reduce the number of parameters that need to be optimized to 1%–10% of full fine-tuning.60% similarUnverifiedMost friendly evaluation tasks can be passed with Sliding Window Attention (SWA), so combining a method with SWA allows reporting compression ratios or sparsity levels of 5–10×.57% similarVerifiedExpected Calibration Error (ECE) bins prediction samples by confidence level, computes the weighted average of the difference between predicted confidence and actual accuracy within each bin, and ideally approaches 0.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1009423API
curl https://kongchang.com/api/v1/knowledge/claims/1009423MCP
get_claim(id=1009423)