Multi-Agent Intelligent System For Dynamic Predictive Evaluation Of National And Regional Labour Markets In Bulgaria

Reliable public-sector labour-market forecasting requires models that can be updated as data sources, AI tools, and labour-market signals evolve. This paper proposes a provider-independent multi-agent framework for dynamic predictive evaluation of national and regional labour markets in Bulgaria. Implemented as a Model Context Protocol (MCP) server, the system coordinates specialised agents for data ingestion, preprocessing, semantic extraction, AI-adjusted transformation modelling, automated model evaluation, and reporting through stable input-output contracts. The empirical application integrates Bulgarian Employment Agency administrative registered-unemployment indicators, Eurostat labour-market data, World Bank macroeconomic data, and text/audio/video evidence on AI, skills, and employment change. The study period covers 2015–2030, combining observed official inputs for 2015–2025 with forecast/scenario outputs for 2026–2030. For youth unemployment under 25, the semantic-enhanced model achieves the best predictive accuracy (RMSE = 0.2033; MAE = 0.1457), representing a small improvement over the structured baseline (RMSE = 0.2057; MAE = 0.1462) and a substantial RMSE reduction relative to the persistence benchmark (RMSE = 0.4750; MAE = 0.2891). Regional forecasts indicate persistent spatial inequality, with the Northwest remaining the highest-risk region and the Southwest the lowest-risk region.