FORECASTING THE BEHAVIOR OF TARGET SEGMENTS TO ACTIVATE ADVERTISING TOOLS: CASE OF MOBILE OPERATOR VODAFONE UKRAINE

Abstract

Today, the use of machine learning technology in combination with the use
of big data are topics that are actively discussed in business around the world.
This topic has long gone beyond the information sphere, as it now applies to
almost every sphere of life: economic, telecommunications, education, medicine,
administration, and especially defense. Predicting customer behavior based on
scoring models is in its infancy in Ukrainian companies, the main ones being
the introduction of artificial intelligence technologies and machine learning,
which will be the leading catalyst that will facilitate decision-making in business
in the nearest future. The aim of the study is to develop a scoring model that
predicts the behavior of target segments, namely, updating their activity to
activate advertising tools. To achieve the goal of the work a set of research
methods was used: dialectical – to reveal the theoretical foundations of models
and types of forecasting models; analytical – in the study of the functioning of
the environment SAS, Anaconda; optimization methods – to choose the best
model and generate features. Scientific novelty and theoretical significance lie
in the development of a scoring model for predicting the activity of subscribers
of the telecommunications company “VF Ukraine”, on the basis of which
marketing campaigns are conducted. With the help of the built-in scoring model,
the company “VF Ukraine” can target its campaigns to retain subscribers. The
marketing directorate of the enterprise can choose the TOP-20 or TOP-30 of the
most prone subscribers to non-resumption of activity, i.e., tend to switch to other
mobile operators, and hold promotions for them – providing additional gifts and
bonuses, money to mobile account.