Nutrient enrichment of aquatic ecosystems caused dramatic increase in the frequency, magnitude and duration of cyanobacterial blooms. Such blooms may cause fish kills, have adverse health effects on humans and contribute to the loss of biodiversity in aquatic ecosystems. Some 50 eutrophic to hypereutrophic ponds from the Brussels Capital Region (Belgium) were studied between 2003 and 2009. A number of the ponds studied are prone to persistent cyanobacterial blooms. Because of the related health concerns and adverse effects on ecological quality of the affected ponds, a tool for assessment of the risk of cyanobacterial bloom occurrence was needed. The data acquired showed that cyanobacteria have threshold relationships with most of the environmental factors that control them. This is negatively reflected on the predictive capacity of conventional statistical methods based on linear relationships. Therefore, classification trees designed for the treatment of complex data and non-linear relationships were used to assess the risk of cyanobacterial bloom occurrence. The main factors determining cyanobacterial bloom development appeared to be phytoplankton biomass, pH and, to a lesser degree, nitrogen availability. These results suggest that to outcompete eukaryotic phytoplankters cyanobacteria need the presence of environmental constraints: carbon limitation, light limitation and nitrogen limitation, for which they developed a number of adaptations. In the absence of constraints, eukaryotic phytoplankters appear to be more competitive. Therefore, prior build up of phytoplankton biomass seems to be essential for cyanobacterial dominance. Classification trees proved to be an efficient tool for the bloom risk assessment and allowed the main factors controlling bloom development to be identified as well as the risk of bloom occurrence corresponding to the conditions determined by these factors to be quantified. The results produced by the classification trees are consistent with those obtained earlier by probabilistic approach to bloom risk assessment. They can facilitate planning management interventions and setting restoration priorities.