Vol.13, No.1, February 2024.                                                                                                                                                                               ISSN: 2217-8309

                                                                                                                                                                                                                        eISSN: 2217-8333

TEM Journal

TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS

Association for Information Communication Technology Education and Science

Unlocking Automated Machine Learning Efficiency: Meta-Learning Dynamics in Social Sciences for Education and Business Data

Dijana Oreški, Dunja Višnjić, Nikola Kadoić

© 2024 Dijana Oreški, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)

Citation Information: TEM Journal. Volume 13, Issue 1, Pages 797-808, ISSN 2217-8309, DOI: 10.18421/TEM131-82, February 2024.

Received: 03 October 2023.

Revised:   22 December 2023.
Accepted: 16 January 2024.
Published: 27 February 2024.

Abstract:

Automated Machine Learning (AutoML) utilizing meta-learning (M-L) has gained prominence in the scientific community. Current M-L methods necessitate substantial data and computational resources for extracting meta-features encoding data properties. However, the time needed for meta-feature extraction exceeds that for predictions in M-L systems. This article proposes a domain-specific M-L paradigm tailored to social science, aiming to identify universally applicable meta-features in social science data. Investigating domain-specific properties, the study discerned common meta-features across social science domains, facilitating an efficient AutoML strategy with reduced data requirements. Ninety meta-features, clustered into eight groups characterizing social science data, were employed, focusing on education and business domains. An analysis of 46 datasets revealed domain-specific variations in meta-feature values, confirmed by Wilcoxon tests. Notably, certain meta-features exhibited consistency across social science domains, demonstrating potential for cross-domain AutoML adoption. This research introduces a targeted M-L approach, optimizing AutoML efficiency for social science applications by identifying common meta-features across diverse domains.

Keywords –Meta learning, meta-features, domain meta-learning, domain-specific machine learning.

-----------------------------------------------------------------------------------------------------------

Full text PDF >  

-----------------------------------------------------------------------------------------------------------