Page 65 - eBook_Proceedings of the International Conference on Digital Manufacturing V1

LEVERAGING MACHINE LEARNING
TO ENHANCE SUPPLY CHAIN

AGILITY AND STRATEGIC
OPERATIONAL EXCELLENCE

Muhammad Danish Saleem (NED University of Engineering and
Technology)*, Muhammad Wasif (NED University of Engineering
and Technology)

ABSTRACT

In the context of an increasingly volatile and competitive global
market after the emergence of Industry 4.0, supply chains are also
experiencing an extensive pressure to adapt with agility and
efficiency due to fluctuating demand patterns, operational
disruptions, and logistical uncertainties. This paper introduces a
machine learning based methodology for augmenting the supply
chain agility and achieving the strategic operational excellence,
with a specific focus on the optimisation of demand forecasting.
Demand forecasting is an essential element of supply chain
management, directly influencing procurement, inventory
optimisation, and distribution strategies. Traditional forecasting
approaches often fail to capture the inherent nonlinearities of
market behaviour and adapt to real-time market dynamics, thereby
resulting in inefficiencies and escalated costs. To address these
shortcomings, an intelligent predictive model is designed and
evaluated by utilising historical and empirical datasets from
industry, leading to the comparative analysis of advanced machine
learning algorithms. These algorithms were selected for their
superior capacity to model complex, high-dimensional datasets,
and their robust ability to reduce overfitting through ensemble
learning techniques. Furthermore, a rigorous process of data
preprocessing, model training, and iterative validation is being
followed. The findings underscore that machine learning can
substantially mitigate forecast errors, enhance supply chain

49