Find in Library

Demographic data are fairly accessible data sets that can be used for analysis with the use of modern technologies of artificial intelligence and machine learning (ML). However, they cannot be used for these purposes without special preparatory procedures. Preparatory measures include procedures involving work with signs, work with missing data, their normalization and design of signs. The article on the example of "Distribution of the population by age groups" shows the features of demographic data and suggests approaches for their preparation for the subsequent use of artificial intelligence technologies and machine learning for their analysis. The study allowed us to obtain the following results. It has been established that demographic data has a number of features that can be and should be used in the process of improving the quality of data sets for subsequent work with them using artificial intelligence and machine learning technologies. The features of demographic data include, first of all, their temporal ordering, secondly, demographic data have predictable limits of change, which are determined by socio-economic factors, and the absence of significant differences between the closest values ​​of the observed data. Demographic data is influenced by processes in a sociopolitical and economic society in different historical periods, which must be taken into account when working with demographic data. Demographic data that can be attributed to certain historical periods should be given special attention since their values ​​can both improve the quality of the data set for machine processing and cause the occurrence and growth of systematic and random errors. The proposed approaches can have a practical application to solving problems of population forecasting, determining the structure and composition of age groups, estimating life expectancy, determining the composition of the working (economically active) age population and a number of other tasks.