An Investigation on Machine Learning Approaches in Supply Chain Forecasting: A Survey
1K. Prahathish, J. Naren, Dr.G. Vithya, S. Akhil, K. Dinesh Kumar and S. Sai Krishna Mohan Gupta
Forecasting necessitates the important decision making in Supply Chain network. Recently, machine learning techniques has leveraged towards increasing the forecast accuracy thereby reducing errors. In this work, brief analysis over various machine learning techniques in demand forecasting, demand uncertainty, intermittent demand, reducing bullwhip effect, available in the literature has been surveyed. Demand across echelons of the chain varies as each participant creates various demands. Hence, there is a need for forecasting such scenarios where meeting uncertainties in the future might effectively contribute to the efficient functioning of Supply Chain.
Supply Chain, Forecast, Demand, Artificial Neural Network, Logistics, Support Vector Machine, Bullwhip Effect, Inventory.