Optimized Machine Learning Models for Poverty Detection: A Scientific Review of Multidimensional Approaches

Abstract / Description

This paper presents an optimized machine learning framework for multidimensional poverty detection by integrating empirical validation, comparative performance analysis, and practical deployment strategies. The proposed Optimized Machine Learning Model (OMLM) is evaluated using real-world datasets and compared against conventional approaches including Logistic Regression, Decision Trees, and Convolutional Neural Networks (CNNs). The study demonstrates improved predictive accuracy, adaptability, and computational efficiency through the integration of Genetic Algorithms (GA) and Reinforcement Learning (RL). The paper further discusses cloud deployment, data processing pipelines, regional performance analysis, and practical integration into government policy frameworks, contributing to evidence-based socio-economic planning and data-driven poverty intervention.

Keywords

Suggested Citation