FORECASTING DEMAND AT THE OUTLET–PRODUCT LEVEL IN DISTRIBUTION USING MACHINE LEARNING ALGORITHMS: A CONCEPTUAL MODEL

Ne’matov Abdug‘ani, Ismailov Shixnazar Rashid o‘g‘li, Ashiraliyev Zokirjon Nosirali o‘g‘li

Innores · 2026-yil

Annotatsiya

In the distribution of fast-moving consumer goods (FMCG), the basis for building acorrect plan for sales agents and van-sellers is an accurate forecast of future demandfor each outlet and product. This article — the first part of a three-part series —proposes a conceptual and methodological model for forecasting weekly demand atthe outlet–product (SKU) level using machine learning (ML) algorithms. Based onthe data schema of a real distribution information system (DMS/SFA), it describesthe feature set, the choice of models (Random Forest, XGBoost), and the evaluationmethodology (MAE, RMSE, MAPE, R²). The article provides an integratedframework for practical implementation; empirical verification is intended to becarried out on real data.

Maqola ma’lumotlari
MualliflarNe’matov Abdug‘ani, Ismailov Shixnazar Rashid o‘g‘li, Ashiraliyev Zokirjon Nosirali o‘g‘li
JurnalInnores
Nashr sanasi2026-06-30
Jild2
Son6
Betlar79-85
TilIngliz

Maqolaning asl sahifasi

Kalit so‘zlar

distribution, demand forecasting, machine learning, XGBoost, Random Forest, FMCG, SKU, conceptual model

Ilmiy soha

Texnika

Innores jurnalidan boshqa maqolalar

Innores — barcha maqolalar