Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This work presents a “3 steps–2 aggregation levels” methodological approach for modelling the evolution of the hybriddemand order flow pattern over long time horizons. The hybriddemand is the result of the mutual interaction between the e-commerce and the traditionaldemand. Thus, its modelling requires a complex analysis at various aggregation levels. More specifically, the quantitative modelling and prediction of e-commercedemand is achieved, both at the market (e-sales turnover) and at the operational (order flow) levels. Then, the demand stemming from the traditional sales channels, modified by the e-commerce introduction is specified and formalised. The concurrent presence of dynamic processes and several uncertainty sources as well as the necessity to assess the impact of e-commerce induced demand modifications over a long time horizon justify the development of ademandscenarioplanningapproach.
Nikolaos Geroliminis, Georgios Anagnostopoulos
Tobias Kippenberg, Wenle Weng, Jijun He