Patterns and Factors Determinants in Cases of Missing Persons in Ecuador

Main Article Content

Edwin Xavier Quito Recalde
Johanna Maribel Pando Farez
Edwin Alfred Riofrio Núñez
Paola Dayanara Ramírez Carrión
Jorge Leopoldo Pauta Riera
Dayron Rumbaut Rangel

Abstract

In Ecuador, the problem of disappearances presents an alarming profile that requires deep and multidimensional analysis. This study examines 6,874 cases registered during 2024 using Orange Data Mining, specialized data analysis software, to detect demographic, geographic, and temporal patterns. The findings reveal a resolution rate of 82.1%, with significant fluctuations between regions and population groups. Women represent the most vulnerable group to disappearances, while men who are not located present a higher probability of fatal outcomes. The provinces of Pichincha and Guayas concentrate 46% of the analyzed cases. The study implements a neutrosophic multicriteria model to evaluate the inherent uncertainty in the data, allowing a more robust analysis of fuzzy and indeterminate factors present in disappearance cases. The average age range of affected individuals is 24 years, with a predominance of adolescents. The identified critical period spans from June to September, where causes such as human trafficking and sexual abuse show higher incidence. Evidence-based intervention strategies are proposed, including early warning systems, differentiated protocols by risk profile, and specific preventive programs for adolescents, supported by neutrosophic logic to handle uncertain variables in institutional decision-making.

Downloads

Download data is not yet available.

Article Details

How to Cite
Patterns and Factors Determinants in Cases of Missing Persons in Ecuador. (2025). Neutrosophic Computing and Machine Learning. ISSN 2574-1101, 37, 47-59. https://fs.unm.edu/NCML2/index.php/112/article/view/699
Section
Articles

How to Cite

Patterns and Factors Determinants in Cases of Missing Persons in Ecuador. (2025). Neutrosophic Computing and Machine Learning. ISSN 2574-1101, 37, 47-59. https://fs.unm.edu/NCML2/index.php/112/article/view/699