Implementation of knowledge distillation in developing a prediction model to know the performance of air transportation vocational education using machine learning DOI Open Access

Daniel Dewantoro Rumani,

Darmeli Nasution,

Okvi Nugroho

et al.

Eastern-European Journal of Enterprise Technologies, Journal Year: 2024, Volume and Issue: 6(3 (132)), P. 58 - 65

Published: Dec. 24, 2024

The object of this research is the performance air transportation vocational education. problem in that must be solved complexity model machine learning which requires a long processing time and high resources, so knowledge transfer process distillation carried out carefully student can capture reproduce from teacher's model. without loss accuracy problems such as Good Corporate Governance, Organizational Flexibility, Strategic Change Management variables, are interrelated difficult to accurately. results obtained form predict education by utilizing distillation. interpretation apply XGBoost algorithm characteristics teacher has best terms loss, while with shows significant reduction compared training Thus, proven help models models, producing prediction up 90 % being an efficient alternative predicting influence main factors on These findings expected provide contribution development more effective context education, especially field

Language: Английский

Generative AI-Assisted Evaluation of ESG Practices and Information Delays in ESG Ratings DOI
Q Wang

Finance research letters, Journal Year: 2025, Volume and Issue: unknown, P. 106757 - 106757

Published: Jan. 1, 2025

Language: Английский

Citations

0
Implementation of knowledge distillation in developing a prediction model to know the performance of air transportation vocational education using machine learning DOI Open Access

Daniel Dewantoro Rumani,

Darmeli Nasution,

Okvi Nugroho

et al.

Eastern-European Journal of Enterprise Technologies, Journal Year: 2024, Volume and Issue: 6(3 (132)), P. 58 - 65

Published: Dec. 24, 2024

The object of this research is the performance air transportation vocational education. problem in that must be solved complexity model machine learning which requires a long processing time and high resources, so knowledge transfer process distillation carried out carefully student can capture reproduce from teacher's model. without loss accuracy problems such as Good Corporate Governance, Organizational Flexibility, Strategic Change Management variables, are interrelated difficult to accurately. results obtained form predict education by utilizing distillation. interpretation apply XGBoost algorithm characteristics teacher has best terms loss, while with shows significant reduction compared training Thus, proven help models models, producing prediction up 90 % being an efficient alternative predicting influence main factors on These findings expected provide contribution development more effective context education, especially field

Language: Английский

Citations

0