ON APPROACHES TO ANALYZING DEMOGRAPHIC DATA USING MACHINE LEARNING
Journal Title: Современные информационные технологии и ИТ-образование - Year 2018, Vol 14, Issue 4
Abstract
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.
Authors and Affiliations
Anatolii Solovev, Stefan Solovev
Keywords
Related Articles
- EP ID EP523585
- DOI 10.25559/SITITO.14.201804.947-959
- Views 141
- Downloads 0
THE CHOICE OF TECHNOLOGICAL SOLUTIONS FOR SOFTWARE DEVELOPMENT FOR DISTRIBUTED INFORMATION SYSTEMS
The choice of tools and programming technologies for creating information systems is a current trend. Each projected system needs you to define a set of criteria for the development environment used by libraries and tech...
THE EXPERIENCE OF UPDATING THE EDUCATIONAL STANDARDS OF HIGHER EDUCATION IN THE FIELD OF ICT
The article describes the experience of Russian universities in integrating professional and educational standards in the design of higher education educational programs in the field of information and communication tech...
DYNAMIC ONTOLOGY BASED RETRIEVAL AND ANALYSIS OF INFORMATION ON SCIENCE AND ENGINEERING
RDF ontologies are proposed as modelling pattern for associations of innovation cycles being performed by science-intensive technical products. An appropriate ontology is applied as framework of personalized archives of...
MATHEMATICAL PROGRAMS MODERNIZATION BASED ON RUSSIAN AND INTERNATIONAL STANDARDS
Russian education standards have come a long way from being extremely detailed and regulating the content of education programs at all levels to the current state when there is a great freedom for universities in definin...
REFACTORING OF THE OPENVZ DRIVER FOR THE OPENNEBULA CLOUD PLATFORM WITHIN THE JINR CLOUD INFRASTRUCTURE PROJECT
This article explores the possibilities of using OpenVZ virtualization technology in the cloud infrastructure of the Joint Institute for Nuclear Research (JINR), built on the OpenNebula platform. OpenNebula is an open a...