Paper Number
1531
Abstract
One of the largest investments of a company is its implementation of an enterprise system. Sometimes, companies, and thus their enterprise systems, face changes that were not foreseen at the time the system was implemented. One example can be found in the COVID-19 pandemic in which retailers are facing the huge problem that current forecasting models no longer produce accurate forecasts and changes in feature spaces are needed. In this paper transfer learning and a proposed method, called dropout profiles, are used to react faster to changes in feature space. This method is implemented in a case study with changes in the feature space of a demand forecast. It is shown that the proposed method performs significantly better than traditional methods. In practice, this means that neural networks can expect a longer life cycle and companies can react faster to changes in the market.
Recommended Citation
Hütsch, Marek, "Transfer Learning to enable Flexibility of Demand Forecasting: Dropout Profiles to protect from Negative Transfer" (2021). ECIS 2021 Research Papers. 99.
https://aisel.aisnet.org/ecis2021_rp/99
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.