SMAC or Sequential Model-based Algorithm Configuration is a method for algorithm parameter and model optimisation that allows to find the best performing model in an automated way. SMAC can be found in auto-
weka and other tools.
SMAC is very effective in hyperparameter optimisation of machine learning algorithms.
Besides hyperparameter optimization, SMAC can also be used to detect which input parameters are most significant.
More information on SMAC and background papers can be found on
this link
