EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Study on Machine Learning-Based Cost Estimation Models for AI Training Data Construction

Yoon-Seok Ko, Bong Gyou Lee

Applied Sciences · 17.03.2026 · 16 (6) · 2891

DOI: 10.3390/app16062891 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 17.03.2026. Verfasst von Yoon-Seok Ko und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposes an explainable machine learning framework for estimating the total project cost (TPC) of AI training-data construction, where cost information is difficult to structure due to heterogeneous workflows and quality requirements. Using 386 public AI training-data projects conducted between 2020 and 2022, we derive 24 numerical predictors from standardized final reports and construct three input tracks: a baseline feature set, a principal component analysis (PCA)-enhanced set, and a factor analysis (FA)–enhanced set capturing latent cost structures. Four regression models (Ridge, Random Forest, XGBoost, and LightGBM) are evaluated using nested cross-validation. XGBoost achieves the best overall performance across all three tracks (Baseline, PCA-enhanced, and FA-enhanced). Among them, PCA-enhanced XGBoost attains the highest predictive accuracy (R2 = 0.868; RMSE = 1084.9; MAE = 746.9; MAPE = 0.358; pooled out-of-fold), while Baseline XGBoost yields the lowest MAE (731.4; R2 = 0.863). To support transparent decision-making, Shapley Additive exPlanations (SHAP)-based attribution and scenario-based sensitivity analyses are conducted. Results show that project scale and process-level unit costs are dominant cost-drivers, while cloud usage, expert participation, and de-identification requirements exhibit secondary effects. The proposed framework provides an interpretable, data-driven approach to cost information management and decision support for data-intensive AI projects.

Zitieren

APA

Ko, Y., & Lee, B. G. (2026). A Study on Machine Learning-Based Cost Estimation Models for AI Training Data Construction. Applied Sciences, 16(6), 2891. https://doi.org/10.3390/app16062891

Vancouver

Ko Y, Lee BG. A Study on Machine Learning-Based Cost Estimation Models for AI Training Data Construction. Applied Sciences. 2026;16(6):2891. doi:10.3390/app16062891

BibTeX
@article{Ko2026,
  author = {Ko, Yoon-Seok and Lee, Bong Gyou},
  title = {A Study on Machine Learning-Based Cost Estimation Models for AI Training Data Construction},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {6},
  pages = {2891},
  doi = {10.3390/app16062891}
}
Kostenlos starten →