Here a combined approach is considered to the prediction of intentions of an employee of a company to quit, on the basis of demographic factors and job satisfaction factors. The developed method includes preliminary assessment of reliability of data from staff survey, an analysis of correlation dependence, construction of a regression model and a nonlinear predictor to assess a probability of staff turnover. This method allows an expert not only to identify the employees who fall into a zone of probable turnover, but also to adjust the processes of human resource on the basis of the most critical factors. At the stages of the method, an employee of a company has a possibility to reduce the number of factors (by grouping, or discarding insignificant factors). Such a choice is made both on the basis of mathematical indicators and taking into account the experience of an expert from a human resource department. To preserve an expert component, authors of the present study refused applying the automated methods of reducing dimensionality, such as a Principal Component Analysis. The developed method is implemented on the basis of a logistic regression analysis, which allowed us to select a group of individual factors and aspects of job satisfaction that affect staff turnover. In addition, it was found that salary level and marital status are significant predictors for the intentions of staff turnover