EUVIMEDEUVIMED entdecken
Crossref

AUTOMATED MACHINE LEARNING VERSUS EXPERT-ENGINEERED PREDICTIVE MODELING PIPELINES: A COMPARATIVE PERFORMANCE AND APPLICABILITY STUDY

Sungho Kim, SaffatKamal Niloy, Ulukbek Myrzabekov, Rizwan Ali, Umer Aqeel

International Journal of Grid Computing & Applications · 28.03.2026 · 17 (1) · 101-106

DOI: 10.5121/ijgca.2026.17109 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Grid Computing & Applications, online erschienen am 28.03.2026. Verfasst von Sungho Kim und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated Machine Learning (AutoML) has emerged as a transformative approach in predictive analytics by automating model selection, feature engineering, and hyperparameter tuning. While AutoML enhancesefficiencyand accessibility, expert-crafted machine learning pipelines remain dominant in complex and high-stakes applications. This study presents a comparative evaluation of AutoML systems and human-designed predictive modelingpipelines across performance, interpretability, computational cost, robustness, and business applicability. Experimental results using structured datasets for classification and regression tasks demonstrate that AutoML achieves competitive predictive accuracy with significantly reduced development time. However, expert-crafted models provide superior contextual optimization and interpretability in domain-specific scenarios.

Zitieren

APA

Kim, S., Niloy, S., Myrzabekov, U., Ali, R., & Aqeel, U. (2026). AUTOMATED MACHINE LEARNING VERSUS EXPERT-ENGINEERED PREDICTIVE MODELING PIPELINES: A COMPARATIVE PERFORMANCE AND APPLICABILITY STUDY. International Journal of Grid Computing & Applications, 17(1), 101-106. https://doi.org/10.5121/ijgca.2026.17109

Vancouver

Kim S, Niloy S, Myrzabekov U, Ali R, Aqeel U. AUTOMATED MACHINE LEARNING VERSUS EXPERT-ENGINEERED PREDICTIVE MODELING PIPELINES: A COMPARATIVE PERFORMANCE AND APPLICABILITY STUDY. International Journal of Grid Computing & Applications. 2026;17(1):101-106. doi:10.5121/ijgca.2026.17109

BibTeX
@article{Kim2026,
  author = {Kim, Sungho and Niloy, SaffatKamal and Myrzabekov, Ulukbek and Ali, Rizwan and Aqeel, Umer},
  title = {AUTOMATED MACHINE LEARNING VERSUS EXPERT-ENGINEERED PREDICTIVE MODELING PIPELINES: A COMPARATIVE PERFORMANCE AND APPLICABILITY STUDY},
  journal = {International Journal of Grid Computing & Applications},
  year = {2026},
  volume = {17},
  number = {1},
  pages = {101--106},
  doi = {10.5121/ijgca.2026.17109}
}
Kostenlos starten →