A method includes receiving a first file attribute from a computing device. The method also includes determining whether a classification for a file is available from a first cache of the server based on the first file attribute. The method includes sending the first file attribute from the server to a second server to determine whether the classification for the file is available at a base prediction cache of the second server. The method includes receiving a notification at the server from the second server that the classification for the file is unavailable at the base prediction cache. The method includes, in response to receiving the notification, determining the classification for the file by performing an analysis of a second file attribute based on a trained file classification model. The method includes sending the classification to the computing device and sending at least the classification to the base prediction cache.