EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving Privacy Recommendations Using Explainable AI Techniques

Rahul Rai, Dr. Jeetendra Singh Yadav

International Journal of Scientific Research in Science, Engineering and Technology · 10.01.2026 · 13 (1) · 84-92

DOI: 10.32628/ijsrset26136 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Scientific Research in Science, Engineering and Technology, online erschienen am 10.01.2026. Verfasst von Rahul Rai und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid growth of digital platforms, users are increasingly required to make complex privacy-related decisions, often without fully understanding the consequences of their choices. Traditional privacy recommendation systems focus primarily on accuracy but lack transparency, leading to low user trust and limited adoption. This paper presents an explainable artificial intelligence (XAI)–based framework to improve the effectiveness and transparency of privacy recommendations. The proposed model integrates machine learning–based personalization with explainability techniques to provide users not only with accurate privacy suggestions but also with clear and meaningful explanations for each recommendation. Feature importance analysis and local explanation methods are employed to interpret model decisions and highlight key factors influencing privacy outcomes. Experimental evaluation conducted on real-world and benchmark datasets demonstrates that the proposed approach achieves higher recommendation accuracy, improved user confidence, and better decision consistency when compared with traditional, non-explainable privacy models. Quantitative results indicate a significant improvement in prediction performance, while qualitative analysis confirms enhanced interpretability and user trust. The findings suggest that incorporating XAI techniques into privacy recommendation systems is essential for building transparent, user-centric privacy tools capable of adapting to evolving user preferences and dynamic digital environments.

Zitieren

APA

Rai, R., & Yadav, D. J. S. (2026). Improving Privacy Recommendations Using Explainable AI Techniques. International Journal of Scientific Research in Science, Engineering and Technology, 13(1), 84-92. https://doi.org/10.32628/ijsrset26136

Vancouver

Rai R, Yadav DJS. Improving Privacy Recommendations Using Explainable AI Techniques. International Journal of Scientific Research in Science, Engineering and Technology. 2026;13(1):84-92. doi:10.32628/ijsrset26136

BibTeX
@article{Rai2026,
  author = {Rai, Rahul and Yadav, Dr. Jeetendra Singh},
  title = {Improving Privacy Recommendations Using Explainable AI Techniques},
  journal = {International Journal of Scientific Research in Science, Engineering and Technology},
  year = {2026},
  volume = {13},
  number = {1},
  pages = {84--92},
  doi = {10.32628/ijsrset26136}
}
Kostenlos starten →