This thesis present concise but comprehensive overview of most important paper dedicated to prediction of corporate bankruptcy, as well as overview of the theory behind the employed models and crucial indicators for quality assessment and comparison of the estimations. Manually collected data includes financial statement, identification information and especially specifications of management and responsible persons. From this point of view, data collected are of high quality and in Czech Republic relatively unique. Noticeable is also multiple imputation method used, current "state-of-the-art" technique for missing data treatment. Practical part concentrates on models estimation for various data setting, when contrasting models on raw and truncated datasets. By smoothing data, significantly better model can be estimated with superior discriminating power on the same data points. Inclusion of macroeconomic variables as well as even more significant governance indicators according to current stage of research, improved estimated models.