person the same or is he an imposter (not the real owner of the account). How to properly label such data and use the data for training? How to properly train such a model? someone says that it is necessary to train it as a binary classification, and someone says that this is an anomaly detection task (OneClass SVM), but here and there I don’t understand how to push this data into training. please advise something. Multiclassification is not suitable because there is a very large number of users and it is dynamic.
Hi did someone answer you? I am also looking for special training data about webrequests. Since a few days went by, I would love to hear about your topic ☺️ Has anyone ever tried to build something for webrequests anomalie labeling or training?
Обсуждают сегодня