There is a growing need to precisely quantify the selectivity of large compound sets in high throughput screening, directing investment in lead optimization towards compounds with a high chance of success. High-content, high-density screening technologies such as multiparametric ultra-HTS provide a basis for highly precise screening with unprecedented scope for delineating process artifacts from reliable signals. However, the full potential of these technologies can only be realized with suitable experimental design and sophisticated data analysis tools. We present two advanced analysis workflows demonstrating how multiparametric readouts from a high throughput primary screen can improve decision quality in the hit identification process. The first involves discrete thresholding and the application of multiple selection criteria. The second uses machine learning algorithms and allows an unbiased consideration of all measured parameters.