Abstract : Many models have been proposed to detect breakpoints in chromosomal copy number profiles, but it is usually not obvious to decide which is most effective for a given data set. Furthermore, most methods have a smoothing parameter that determines the number of breakpoints and must be chosen using various heuristics. We present three contributions toward automatic training of smoothing models. First, we propose to select the model and degree of smoothness that maximizes agreement with visual breakpoint region annotations. Second, we develop cross-validation procedures to estimate the error of the trained models. Third, we apply these methods to a new database of annotated neuroblastoma copy number profiles, which we make available as a public benchmark for testing new algorithms. Whereas previous studies have been qualitative or limited to simulated data, our approach is quantitative and suggests which algorithms are fastest and most accurate in practice on real data.