Assessing the quality of scientific conferences is an important and useful service that can be provided by digital libraries and similar systems. This is specially true for fields such as Computer Science and Electric Engineering, where conference publications are crucial. However, the majority of the existing approaches for assessing the quality of publication venues has been proposed for journals. In this paper, we characterize a large number of features that can be used as criteria to assess the quality of scientific conferences and study how these several features can be automatically combined by means of machine learning techniques to effectively perform this task. Within the features studied are citations, submission and acceptance rates, tradition of the conference, and reputation of the program committee members. Among our several findings, we can cite that: (1) separating high quality conferences from medium and low quality ones can be performed quite effectively, but separating the last two types is a much harder task; and (2) citation features followed by those associated with the tradition of the conference are the most important ones for the task.