|
|
|
|
|
|
Article Detail
|
|
Label
|
|
|
Label
|
|
|
|
Design of a Data-Driven Pharmaceutical Inventory Forecasting and Risk Management Framework for Dynamic Hospital Supply Chains
|
|
| Author:
|
, J REVATHI, R JAYADURGA, S RATHIKA
|
| Abstract:
|
The complexity of hospital supply chains and uncertainty in pharmaceutical demand necessitate an
efficient data-driven method for inventory forecasting and risk management. This paper proposes a
detailed framework for creating optimal levels of pharmaceutical inventories, which can reduce the
risk of supply chain disruptions in a rapidly evolving hospital setting. The framework utilizes
historical consumption data, real-time procurement trends, and advanced machine learning models to
predict both short-term and long-term inventory needs accurately. Moreover, it incorporates risk
management tools to identify potential supply disruptions, overstocking, and stockouts, enabling
informed decision-making in advance. The proposed system will have a multi-layered architecture
comprising a data ingestion module, a forecasting engine, a risk analysis module, and a decision
support interface. A hybrid forecasting model is employed, comprising ARIMA, LSTM, and Gradient
Boosted Trees, to make more accurate predictions for the varying drug categories. Simulation-based
stress testing and scenario analysis in various demand and supply scenarios inform the development
of risk-mitigating strategies. It has been validated using actual hospital inventory data, showing 30.5
percent accuracy in the forecast and a mark of 2.73 in the inventory turnover rate, as well as a
decrease in the number of instances requiring emergency purchases. The proposed system
demonstrated an improvement in forecasting of 91 percent over traditional rule-based methods, which
resulted in a 28 percent reduction in stockouts, as well as a 22 percent reduction in holding costs for
inventories. In his paper, the researcher highlights the potential of predictive analytics fueled by AI in
developing resilient and responsive healthcare supply chains. The framework not only ensures optimal
access to drugs but also facilitates evidence-based policy-making and resource allocation in hospital
management, particularly in crises (such as pandemics or supply chain disruptions).
|
| Keyword:
|
Hospital Supply Chains, Pharmaceutical Demand, Inventory Forecasting, Risk Management, Hybrid Forecasting Model, Predictive Analytics, Healthcare Supply Chain Resilience
|
| EOI:
|
-
|
| DOI:
|
https://doi.org/10.31838/ijpr/2021.13.03.245
|
| Download:
|
Request For Article
|
|
|
|
|
|
|
|
|
|
|