The integration of selling and fulfillment processes triggered by omni-channels is transforming the retailer's operations management. In this context, there is a lack of research regarding the connection between digital and physical worlds in retail supply chains. This paper aims to propose a data-driven approach that combines machine-learning demand forecasting and operational planning simulation-based optimization to adaptively synchronize demand and supply in omni-channel retail supply chains. The findings are substantiated through the application of the approach in an omni-channel retail supply chain. The combination of clustering and neural networks improved demand forecast, supporting an assertive identification of demand volume and location. Simulation-based optimization allowed for the definition of which facility would serve identified demands most effectively. The approach reduced fulfillment lead time, mitigated backorders arising from incompatible product´s supply and demand, and lowered operational costs, which are key performance indicators in today's competitive retail markets.
Bibliografisk noteFunding Information:
This work was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES) - Finance Code 001.
This work was financed in part by the Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior - Brasil (CAPES) - Finance Code 001.
© 2020 Elsevier Ltd