Event notification services are used in various applications, for example, stock tickers, environmental monitoring, and facility management. Several filtering algorithms for such services have been proposed. The best performance results are achieved by tree-based algorithms. However, to our knowledge existing algorithms do not consider the influence of event and profile distribution on the filter performance. In this paper we propose a distribution-dependent improvement of the tree-algorithm. We present the test results of our prototypical implementation that show the influence of various distribution-based measures on the performance.