The low digital maturity level, significant fragmentation of available data, and the small data amounts characterize the problematic of existent e-commerce platforms of the Basque Country, according to the experienced collaboration trials. In order to overcome these challenges, we present an e-commerce extension library that collects customer sales predictions and clusterization functionalities grouped into two distinct modules: the Federated learning and personalized module. As a proof of concept, a prototype is presented in this paper that has been developed in the post-Covid context to boost the digitalization capability of small short commerce. |
*** Title, author list and abstract as submitted during Camera-Ready version delivery. Small changes that may have occurred during processing by Springer may not appear in this window.