Applied Ensemble Machine Learning Framework for Data-Driven Decision Support Using Socioeconomic Data

Abstrak

This study presents an applied ensemble machine learning framework for data-driven decision support using socioeconomic and demographic data. The problem is formulated as a supervised regression task, where nonlinear relationships between input variables and outcome indicators are approximated using Random Forest and Gradient Boosting models. The proposed framework emphasizes robustness, interpretability, and practical applicability rather than algorithmic novelty. Experimental results demonstrate that ensemble models achieve stable predictive performance under heterogeneous data conditions. Feature importance analysis highlights the contribution of key socioeconomic factors, illustrating how ensemble learning can support system-level understanding and analytical decision making. A real-world socioeconomic dataset is employed as a case study to demonstrate the applicability of the proposed framework in applied computing and informatics contexts.

Identifier

• DOI: https://doi.org/10.55927/fjmr.v5i1.698
• OpenAlex: https://openalex.org/W7127050623