In machine learning, active class selection (ACS) algorithms aim to intelligently ask for instances of specific classes to optimize a classifier’s performance while minimizing the number of requests. In this paper, we propose a new algorithm (PAL-ACS) that transforms the ACS problem into an active learning problem by introducing pseudo instances. These are used to estimate the usefulness of an upcoming instance for each class using the performance gain model from probabilistic active learning. Our experimental evaluation (on synthetic and real data) shows the advantages of our algorithm compared to state-of-the-art algorithms. Through determining the difficulty of classes, it adapts its sampling proportion and thereby improves the classification performance.