Demand-Driven Inventory Optimization for Regional Pharmaceutical Distribution: Reducing Stockouts, Waste, and Cost Through Data-Driven Forecasting

Two problems dominate regional pharmaceutical distribution: stockouts, where patients cannot get the medicine they need, and overstock, where medicine expires unused and is written off as waste. Both trace back to the same root cause: inaccurate demand forecasts. This paper presents a data-driven demand forecasting framework using five years of real daily pharmacy sales data (2014 to 2019, eight drug categories). A machine learning forecasting model is compared against a naive seasonal baseline, achieving a 23.9% to 26.5% reduction in forecast error (MAE and RMSE). This error reduction is translated into business impact through the standard safety-stock relationship, and combined with a published total-cost-reduction benchmark (13.4%) from risk-based supply chain optimization literature. Applied to illustrative regional inventory and logistics spend scenarios (USD 20M to USD 150M), the framework suggests estimated annual savings of USD 2.68M to USD 20.1M. Limitations and an implementation plan for a regional pharmaceutical operations context are discussed.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-17
DOI
https://doi.org/10.5281/zenodo.24304380
Primary Topic
Supply Chain and Inventory Management
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Demand-Driven Inventory Optimization for Regional Pharmaceutical Distribution: Reducing Stockouts, Waste, and Cost Through Data-Driven Forecasting

Nezar Abdilah Prakasa
2 links
Zenodo (CERN European Organization for Nuclear Research)
Supply Chain and Inventory Management
preprint

Demand-Driven Inventory Optimization for Regional Pharmaceutical Distribution: Reducing Stockouts, Waste, and Cost Through Data-Driven Forecasting

Nezar Abdilah Prakasa
preprint en

Abstract

Two problems dominate regional pharmaceutical distribution: stockouts, where patients cannot get the medicine they need, and overstock, where medicine expires unused and is written off as waste. Both trace back to the same root cause: inaccurate demand forecasts. This paper presents a data-driven demand forecasting framework using five years of real daily pharmacy sales data (2014 to 2019, eight drug categories). A machine learning forecasting model is compared against a naive seasonal baseline, achieving a 23.9% to 26.5% reduction in forecast error (MAE and RMSE). This error reduction is translated into business impact through the standard safety-stock relationship, and combined with a published total-cost-reduction benchmark (13.4%) from risk-based supply chain optimization literature. Applied to illustrative regional inventory and logistics spend scenarios (USD 20M to USD 150M), the framework suggests estimated annual savings of USD 2.68M to USD 20.1M. Limitations and an implementation plan for a regional pharmaceutical operations context are discussed.

Zenodo (CERN European Organization for Nuclear Research)
Supply Chain and Inventory Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon