Team voyTECH: User Activity Modeling with Boosting Trees
This work addresses subscription prediction for Twitch users, representing an incremental improvement in a specific domain.
The authors tackled the problem of predicting Twitch user subscriptions to channels by modeling user activity with boosting trees, achieving winning results in the ECML-PKDD ChAT Discovery Challenge 2020.
This paper describes our winning solution for the ECML-PKDD ChAT Discovery Challenge 2020. We show that whether or not a Twitch user has subscribed to a channel can be well predicted by modeling user activity with boosting trees. We introduce the connection between target-encodings and boosting trees in the context of high cardinality categoricals and find that modeling user activity is more powerful then direct modeling of content when encoded properly and combined with a suitable optimization approach.