{"paper":{"title":"A Horizon-Aware Decision-Support Framework for Demand Forecasting Model Selection in Resilient Production Planning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Projecting test-horizon error metrics forward to the operational horizon improves model selection for multi-step demand forecasting.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adolfo Gonz\\'alez, V\\'ictor Parada","submitted_at":"2026-02-15T00:24:46Z","abstract_excerpt":"Demand forecasting is a critical input for resilient production planning, inventory replenishment, procurement, and capacity decisions under demand intermittency, high variability, and operational uncertainty. In these contexts, selecting forecasting models solely on the basis of fixed test-horizon performance may lead to decisions misaligned with the future planning horizons in which forecasts are used. This study proposes the Metric Degradation by Forecast Horizon (MDFH) procedure as a horizon-aware decision-support framework for selecting demand forecasting models. MDFH projects eligible ou"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MDFH provides a coherent basis for horizon-aware selector design, that RMSSEh and AHSIV remain competitive across heterogeneous demand environments, and that AHSIV adds robustness in structurally complex settings.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The projection of error metrics from test horizon to operational horizon relies on structural stability conditions that are assumed but not shown to hold across the evaluated datasets or real-world shifts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MDFH projects test-horizon error metrics to future horizons under stability assumptions, yielding RMSSEh and the adaptive AHSIV selector that outperform static methods on Walmart, M3, M4, and M5 data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Projecting test-horizon error metrics forward to the operational horizon improves model selection for multi-step demand forecasting.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3353ae59f3f30cdaa115714a38d3a433709cf4fd4493778eae4d40973c59aa26"},"source":{"id":"2602.13939","kind":"arxiv","version":6},"verdict":{"id":"1716fc5d-b08f-4106-a38f-e21ef395d0dc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T21:51:59.511153Z","strongest_claim":"MDFH provides a coherent basis for horizon-aware selector design, that RMSSEh and AHSIV remain competitive across heterogeneous demand environments, and that AHSIV adds robustness in structurally complex settings.","one_line_summary":"MDFH projects test-horizon error metrics to future horizons under stability assumptions, yielding RMSSEh and the adaptive AHSIV selector that outperform static methods on Walmart, M3, M4, and M5 data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The projection of error metrics from test horizon to operational horizon relies on structural stability conditions that are assumed but not shown to hold across the evaluated datasets or real-world shifts.","pith_extraction_headline":"Projecting test-horizon error metrics forward to the operational horizon improves model selection for multi-step demand forecasting."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.13939/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}