EUVIMEDEUVIMED entdecken
Crossref

AI-Driven Inventory Replenishment in U.S. Wholesale Distribution: Outcomes of Predictive Model Implementation

Md Hasanujamman Bari

International Journal of Scientific Interdisciplinary Research · 01.10.2026 · 16 (10) · 01-40

DOI: 10.63125/j4y8gp20 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Scientific Interdisciplinary Research, online erschienen am 01.10.2026. Verfasst von Md Hasanujamman Bari.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wholesale distributors in the United States hold large inventories to serve business customers from stock, and their replenishment decisions are increasingly driven by predictive models: statistical and machine-learning forecasts, advanced planning systems, automated replenishment and collaborative arrangements with suppliers. The outcomes of such implementations are reported in case studies, before-after comparisons, surveys and evaluations on company data. This systematic review covers the literature published before 2020 on the implementation of predictive and data-driven models in inventory replenishment in distribution settings, with wholesale distribution and United States evidence in focus. A reproducible search of the Crossref index with 28 strings returned 5,600 records (3,936 unique); 3,163 titles and 392 abstracts were screened against pre-registered criteria and 119 studies were included and coded for sector, country, replenishment decision, model and system type, measurement design, outcomes with their direction and magnitude, implementation factors and ten reporting items; an independent 10% re-screening estimated consistency. Reported outcomes are predominantly favourable: cost, service and inventory improvements are the most frequently reported, but 27% of the studies rest on descriptive case narratives or self-reported surveys, baselines and observation periods are stated in a minority, and United States wholesale distributors are the explicit setting of only 1 study. Machine-learning components appear in 12% of the studies and almost all after 2010. The findings support an outcomes-measurement framework for AI-driven replenishment in a wholesale distributor: a baseline, a stated policy, paired inventory and service measures, an observation period that spans a demand cycle, a control group of SKUs or branches, and a reporting checklist. Limitations are single-reviewer, abstract-based screening and one bibliographic index.

Zitieren

APA

Bari, M. H. (2026). AI-Driven Inventory Replenishment in U.S. Wholesale Distribution: Outcomes of Predictive Model Implementation. International Journal of Scientific Interdisciplinary Research, 16(10), 01-40. https://doi.org/10.63125/j4y8gp20

Vancouver

Bari MH. AI-Driven Inventory Replenishment in U.S. Wholesale Distribution: Outcomes of Predictive Model Implementation. International Journal of Scientific Interdisciplinary Research. 2026;16(10):01-40. doi:10.63125/j4y8gp20

BibTeX
@article{Bari2026,
  author = {Bari, Md Hasanujamman},
  title = {AI-Driven Inventory Replenishment in U.S. Wholesale Distribution: Outcomes of Predictive Model Implementation},
  journal = {International Journal of Scientific Interdisciplinary Research},
  year = {2026},
  volume = {16},
  number = {10},
  pages = {01--40},
  doi = {10.63125/j4y8gp20}
}
Kostenlos starten →