MULTI-MODAL ENSEMBLE LEARNING ARCHITECTURE FOR LABOR MARKET’S DIGITAL TRANSFORMATION

Assylbek Gizatov, Nurtas Zhaksybayev, Alibi Jangeldin

2026

Closed access Metadata (CSL-JSON)
DOI 10.68458/ee.2026.1.6
Data confidence 85 high
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The rapid growth of educational grants in Kazakhstan has led to wage stagnation and oversaturation in key sectors. This study presents a meta-model combining CatBoost, Explainable Boosting Machine (EBM), and Bayesian-optimized LSTM neural networks to forecast wages, analyze labor market factors, and predict sector demand trends. Findings highlight critical oversupply risks, providing policymakers actionable insights for aligning education with economic needs, fostering sustainable development.