FIELD: computer equipment.
SUBSTANCE: group of inventions relates to computer engineering and can be used to create a predictive model. Categorical factor is associated with a training object used to train the machine learning algorithm (MLA). Method comprises stages, at which MLA is trained by means of several models, besides, each model includes multiple decision trees (ensemble of solutions), for each model, the corresponding set of training objects is organized into an ordered list of training objects such that for each training object there is at least one of: (i) a previous training object that is before the given training object, and (ii) a subsequent training object that is located after said training object, use a corresponding ordered list for said categorical factor to create a numerical representation of values of said categorical factor.
EFFECT: technical result is conversion of categorical factor into its numerical representation.
20 cl, 14 dwg, 1 application
