Search

The telecommunications market is well developed but is characterized by oversaturation and high levels of competition. Based on this, the urgent problem is to retain customers and predict the outflow of customer base by switching subscribers to the services of competitors. Data Science technologies and data mining methodology create significant opportunities for companies that implement data analysis and modeling for development of customer churn prediction models. The research goals are to compare different approaches and methods for customer churn prediction and construct different Data Science models to classify customers according to the probability of their churn from the company’s client base and predict potential customers who could stop to use the company’s services. On the example of one of the leading Ukrainian telecommunication companies, the article presents the results of different classification models, such as C5.0, KNN, Neural Net, Ensemble, Random Tree, Neural Net Ensemble, etc. All models are prepared in IBM SPSS Modeler and have a high level of quality (the overall accuracy and AUC ROC are more than 90%). So, the research proves the possibility and feasibility of using models in the further classification of customers to predict customer loyalty to the company and minimize consumer’s churn. The key factors influencing the customer churn are identified and form a basis for future prediction of customer outflow and optimization of company’s services. Implementation of customer churn prediction models will help to maintain customer loyalty, reduce customer outflow and increase business results

This research utilizes intellectual data analysis to deepen insights into educational dynamics by examining university professors' behavioral responses to education management amidst socioeconomic uncertainty. The study applied sophisticated regression and cluster analysis tools to sociological survey data, focusing on professors' attitudes toward distance education. The survey assessed perceptions of its advantages and disadvantages, aiming to uncover factors influencing professors' inclinations toward this mode of teaching. Results revealed six distinct behavioral "profiles" or clusters of professors, each with unique responses to distance education. These insights guide recommendations for educational policy priorities aimed at addressing weaknesses in education management. Key strategies proposed include forming databases of behavioral responses and employing algorithms for deep intellectual analysis. Such measures intend to align educational practices with the values, welfare needs, and communication preferences of the scholarly community, thereby enhancing their propensity for distance education. The study concludes that a higher level of academic engagement in distance education can be achieved by tailoring educational strategies to the specific needs and values of different professor groups. This approach promises to improve the effectiveness of education management and the overall quality of education, benefiting both professors and students by creating a more supportive and effective teaching environment. [ABSTRACT FROM AUTHOR]

The impact of the war in Ukraine and migration has affected the ecommerce markets of the recipient countries, presenting both opportunities, in the form of an increased consumer base, and challenges, such as the lack of a clear development vision. This paper aims to investigate the influence of migration processes on the development of e-commerce in Poland and examine the feasibility of using forecasting methods by e-commerce companies under these conditions for future activity planning. To fulfill the research objective, the following tasks were addressed: investigating the current state of e-commerce development influenced by migration processes; exploring modern migration processes and their impact on global economies; assessing the impact of migration from Ukraine on the Polish market; and analyzing a Polish online store to develop a model for forecasting data and planning activities under the influence of migration processes. To achieve this goal, three models were constructed: a multiple regression model to assess the level of migration processes' influence on e-commerce; a neural network to forecast sales for a Polish e-commerce store; and cluster analysis to identify clusters of goods most affected by migration processes. The study analyzed the nuances of modern migration processes and assessed the reverse effect of migration as a driver of e-commerce development. Migration stimulates e-commerce by altering consumer behavior and logistics routes, increasing exports and imports, and fostering the spread of digital entrepreneurship. Using data from a Polish online store, the study modeled the impact of market changes on the company's operations and identified the most significant factors. Thus, the analysis explored the impact of migration on ebusiness in Poland through constructed models. Regression analysis revealed that migration processes have contributed to the development of the Polish online store's sales, thanks to the increase in migrant consumers and rising price levels. A neural network was developed with machine learning, incorporating macroeconomic and demographic factors into its forecasting typology. Cluster analysis was employed to examine the online store's assortment, identifying clusters by sales volume and migrants' influence. The analysis determined that, following the onset of the migration movement, categories experiencing a surge in demand from refugees, such as baby food products, appliances, telephones, furniture, and communication devices, saw the most significant growth. [ABSTRACT FROM AUTHOR]