EUVIMEDEUVIMED entdecken
Crossref

Marketing Strategy Development in Insurance Using Data Science

Tetiana Zatonatska, Yana Fareniuk, Alexandra Albuquerque, Daryna Vorontsova, Yehor Horiachev

Marketing and Management of Innovations · 30.06.2026 · 17 (2) · 1

DOI: 10.21272/mmi.2026.2-01 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Marketing and Management of Innovations, online erschienen am 30.06.2026. Verfasst von Tetiana Zatonatska und 4 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accelerating digital transformation of the insurance sector intensified competitive pressure, and the expanding use of data science technologies have substantially reshaped marketing strategy formation, creating new opportunities for more precise customer segmentation, predictive analytics, and strategic optimization in insurance companies. The aim of this paper is to examine how data science techniques can be operationalized to support marketing strategy formation in the Ukrainian insurance market, which is characterized by high uncertainty and structural transformation. This study addresses three research questions: which customer attributes are the most significant determinants of insurance product selection in the Ukrainian insurance market; to what extent can decision tree models provide accurate and interpretable segmentation for insurance marketing purposes; and how can the results of data science models be translated into actionable insights for marketing strategy implementation by insurers and practitioners? Using anonymized customer relationship management (CRM) data from a top-10 Ukrainian insurer (N = 14,000 clients), a decision tree classification model was developed to identify key determinants of insurance product choice. Model performance was evaluated using accuracy metrics and rule support. A qualitative description was employed to support audience interpretation. The results indicate that customer loyalty (measured by the number of active contracts), geographic location, and age are the most significant predictors of insurance product selection, with an overall classification accuracy of 93.5%. The extracted decision rules provide transparent and interpretable insights that can be directly translated into targeted marketing actions. The findings demonstrate how interpretable machine learning models can support data-driven targeting, improve marketing return on investment (ROI), and enhance personalization in insurance services. The study highlights key areas of data science application in insurance marketing, including customer segmentation, targeted marketing, and campaign optimization. This study contributes empirical evidence from an under researched, high-uncertainty market and proposes a structured, interpretable analytics approach based on classical machine learning for insurance marketing strategy development. It bridges the gap between analytical modelling and practical marketing strategy, offering insights that are directly applicable to insurance practitioners

Zitieren

APA

Zatonatska, T., Fareniuk, Y., Albuquerque, A., Vorontsova, D., & Horiachev, Y. (2026). Marketing Strategy Development in Insurance Using Data Science. Marketing and Management of Innovations, 17(2), 1. https://doi.org/10.21272/mmi.2026.2-01

Vancouver

Zatonatska T, Fareniuk Y, Albuquerque A, Vorontsova D, Horiachev Y. Marketing Strategy Development in Insurance Using Data Science. Marketing and Management of Innovations. 2026;17(2):1. doi:10.21272/mmi.2026.2-01

BibTeX
@article{Zatonatska2026,
  author = {Zatonatska, Tetiana and Fareniuk, Yana and Albuquerque, Alexandra and Vorontsova, Daryna and Horiachev, Yehor},
  title = {Marketing Strategy Development in Insurance Using Data Science},
  journal = {Marketing and Management of Innovations},
  year = {2026},
  volume = {17},
  number = {2},
  pages = {1},
  doi = {10.21272/mmi.2026.2-01}
}
Kostenlos starten →