EUVIMEDEUVIMED entdecken
Crossref

Data Quality Enhancement Techniques Using Artificial Intelligence

Eng.Ziad Tawfik Mostafa shaeb, Eng.Abdalgader Egreira Ali Abuhamra

IOSR Journal of Computer Engineering · 2026-05 · 28 (5) · 62-71

DOI: 10.9790/0661-2805016271 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IOSR Journal of Computer Engineering, 2026-05. Verfasst von Eng.Ziad Tawfik Mostafa shaeb und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Data quality serves as the bedrock of reliable decision-making in the modern digital economy, yet traditional manual cleaning methods are increasingly inadequate for the sheer volume and velocity of contemporary "Big Data." This research explores the transformative role of Artificial Intelligence (AI) and Machine Learning (ML) in automating and optimizing data quality enhancement processes. By leveraging sophisticated algorithms, organizations can move beyond static rules-based systems to dynamic, self-learning frameworks capable of identifying complex patterns and anomalies. The core of this study examines key techniques such as automated data profiling, intelligent entity resolution, and predictive missing-value imputation. AI-driven models, particularly Deep Learning and Natural Language Processing (NLP), are highlighted for their ability to handle unstructured data formats and resolve semantic inconsistencies that human operators might overlook. Furthermore, the integration of Reinforcement Learning allows systems to continuously improve their accuracy based on feedback loops, reducing the technical debt associated with "dirty data." The paper also addresses the critical challenges of algorithmic bias and the necessity for "Human-in-the-Loop" (HITL) configurations to ensure transparency and ethical standards. Ultimately, this research demonstrates that AI-based enhancement not only reduces operational costs and manual labor but also significantly elevates the integrity and trustworthiness of data assets. By implementing these advanced techniques, enterprises can unlock the true potential of their analytical engines, leading to more precise forecasting, enhanced customer experiences, and robust strategic insights. This abstract concludes that the future of data management lies in the seamless convergence of AI and data governance, creating a resilient foundation for the next generation of intelligent systems and autonomous enterprises.

Zitieren

APA

shaeb, E. T. M., & Abuhamra, E. E. A. (2026). Data Quality Enhancement Techniques Using Artificial Intelligence. IOSR Journal of Computer Engineering, 28(5), 62-71. https://doi.org/10.9790/0661-2805016271

Vancouver

shaeb ETM, Abuhamra EEA. Data Quality Enhancement Techniques Using Artificial Intelligence. IOSR Journal of Computer Engineering. 2026;28(5):62-71. doi:10.9790/0661-2805016271

BibTeX
@article{shaeb2026,
  author = {shaeb, Eng.Ziad Tawfik Mostafa and Abuhamra, Eng.Abdalgader Egreira Ali},
  title = {Data Quality Enhancement Techniques Using Artificial Intelligence},
  journal = {IOSR Journal of Computer Engineering},
  year = {2026},
  volume = {28},
  number = {5},
  pages = {62--71},
  doi = {10.9790/0661-2805016271}
}
Kostenlos starten →