BUILDING THE NEXT GENERATION PERSONAL DATA PLATFORMS
DKE: User Profiling System
The User Profiling System (Part of the DKE) is able to automatically generate user profiles from the sequences of hosts visited by users.
The User Profiling System is developed in Python and makes use of the Gensim library to train a skipgram model for the network hosts
The project is open-source and its code is on the online repository:
The User Profiling System is released under the NLE’s academic or non-profit organization non-commercial research only, see the LICENSE file in the project repository.
Copyright (C) 2021 NEC Laboratories Europe
- Roberto González, David Friede, Mathias Niepert
In this video we show how the User Profiling System can:
- Generate profiles at line rate for several thosands of users
- Generate profiles for a given set of hostnames (similar to the Demonstration above in the blue button)
- Work with network data even if third party cookies are not allowed