Аннотация:Predictive analytics is a field of knowledge that allows you to make informeddecisions, prepare for unforeseen situations and anticipate all kinds of emergencies. Recently,predictive analysis has been actively used in industry: based on historical data, the model makesa probabilistic forecast of the device's behavior in the near future. This paper provides acomparative analysis of two predictive models, which both could self-learn and had the propertyof self-correction. The accuracy of predicting the development of a defect in industrialequipment, as well as the prediction horizon, were evaluated. Particular attention is paid to thepeculiarity of working with data obtained from production sensors