EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

User Engagement Profiling for Online Retail Based on Google Analytics Data

Rohini Sharma, ER. Vanita Rani

International Journal of Scientific Research in Science, Engineering and Technology · 31.10.2025 · 12 (5) · 446-455

DOI: 10.32628/ijsrset2513841 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Scientific Research in Science, Engineering and Technology, online erschienen am 31.10.2025. Verfasst von Rohini Sharma und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates the critical role of user engagement metrics in understanding online user behavior within the e-commerce domain. Leveraging data extracted from Google Analytics (GA) and predictive analytics, this research applies and evaluates machine learning (ML) classification models to enhance digital marketing strategies. Through descriptive statistical analysis, the study examines relationships among key performance indicators (KPIs) such as event count, sessions, purchase revenue, transactions, conversions, and bounce rate to identify factors influencing user engagement. The efficacy of three ML classifiers—Decision Trees (DTs), Naïve Bayes (NB), and k-Nearest Neighbors (k-NN)—was evaluated. Experimental results demonstrate that the Decision Tree model achieved superior performance with a classification accuracy of 97.98%, substantially outperforming Naïve Bayes (65.00%) and slightly exceeding k-Nearest Neighbors (97.90%). Model optimization techniques, including pruning, were implemented to enhance performance and prevent overfitting. The research provides practical, data-driven recommendations for marketing decision-makers to refine digital strategies and improve user engagement. Furthermore, the thesis highlights the transformative potential of integrating artificial intelligence (AI) with web analytics in digital marketing, establishing a robust framework for AI-enhanced, data-driven decision-making processes. This work contributes to both academic knowledge and practical applications in data-driven marketing optimization.

Zitieren

APA

Sharma, R., & Rani, E. V. (2025). User Engagement Profiling for Online Retail Based on Google Analytics Data. International Journal of Scientific Research in Science, Engineering and Technology, 12(5), 446-455. https://doi.org/10.32628/ijsrset2513841

Vancouver

Sharma R, Rani EV. User Engagement Profiling for Online Retail Based on Google Analytics Data. International Journal of Scientific Research in Science, Engineering and Technology. 2025;12(5):446-455. doi:10.32628/ijsrset2513841

BibTeX
@article{Sharma2025,
  author = {Sharma, Rohini and Rani, ER. Vanita},
  title = {User Engagement Profiling for Online Retail Based on Google Analytics Data},
  journal = {International Journal of Scientific Research in Science, Engineering and Technology},
  year = {2025},
  volume = {12},
  number = {5},
  pages = {446--455},
  doi = {10.32628/ijsrset2513841}
}
Kostenlos starten →