Mathematical enhancement of unsupervised machine learning algorithms for optimal lifeline donor knowledge extraction

• DOI: 10.47974/jsms-1282
• Publication Date: 2024-03-30T11:55:24Z
• Authors: P. Ramesh Naidu; Pratik Gite; Vaskar Deka; K. D. V. Prasad; V. Dankan Gowda; Mirzanur Rahman
• Keywords: 0101 mathematics; 01 natural sciences

Lifeline Donor groups are crucial in the field of humanitarian aid because they provide lifesaving times crisis. For effective resource management and coordination, it is to draw relevant insights from donor data a timely manner. Scalability, precision, flexibility responding changing dynamics all areas where traditional techniques knowledge extraction fall short. This study offers fresh method for optimizing databases by utilizing improved unsupervised machine learning methods. In order extract, categorize, prioritize disparate sources, this research presents multi-faceted framework that includes cutting-edge algorithms. By merging developments NLP mining, proposed improves upon classic clustering topic modelling The program able capture subtle semantic links underlying patterns communication using methods like word embedding models graph-based clustering.