| dc.contributor.advisor | Anillo Arrieta, Luis Ángel | |
| dc.coverage.spatial | cead_-_josé_celestino_mutis | |
| dc.creator | Hernández Araque, Jhon Alexander | |
| dc.date.accessioned | 2025-02-21T14:41:06Z | |
| dc.date.available | 2025-02-21T14:41:06Z | |
| dc.date.created | 2024-02-11 | |
| dc.identifier.uri | https://repository.unad.edu.co/handle/10596/67097 | |
| dc.description | | |
| dc.description.abstract | La inseguridad alimentaria es uno de los principales problemas que afrontan los Estados en el
mundo actual. En lugares como Bogotá, este flagelo afecta a un gran número de personas que
habitan en el territorio. Para enfrentar esta problemática, el distrito ha diseñado una serie de
acciones gubernamentales mediante políticas públicas como el CONPES 09 de 2019. En esta
monografía se analiza cómo los modelos de Machine Learning (ML) pueden contribuir a mejorar
la evaluación de la efectividad de la "Política Pública de Seguridad Alimentaria y Nutricional para
Bogotá 2019-2031" a partir de la base de datos recolectada. Se aplicaron múltiples enfoques de
ML, incluyendo modelos supervisados y no supervisados, como regresión lineal, árboles de
decisión, Random Forest y clustering mediante K-means. | |
| dc.format | pdf | |
| dc.title | Modelos de machine learning para la evaluación de la política pública de “seguridad alimentaria y nutricional en Bogotá 2019-2031” | |
| dc.type | Monografía | |
| dc.subject.keywords | Política pública | |
| dc.subject.keywords | Machine Learning | |
| dc.subject.keywords | Seguridad Alimentaria | |
| dc.description.abstractenglish | Food insecurity is one of the main challenges faced by governments worldwide. In places like
Bogotá, this issue affects a significant number of residents. To address this problem, the district
has implemented various governmental actions through public policies such as CONPES 09 of
2019. This monograph analyzes how Machine Learning (ML) models can help improve the
evaluation of the effectiveness of the "Public Policy on Food and Nutritional Security for Bogotá
2019-2031" based on the collected database. Multiple ML approaches were applied, including
supervised and unsupervised models such as linear regression, decision trees, Random Forest, and
K-means clustering. The results showed that decision trees were particularly effective in classifying
and predicting food insecurity, while clustering identified unique patterns in food insecurity and
malnutrition data between 2019 and 2023. This work highlights the importance of integrating ML
techniques into public management to optimize decision-making and maximize policy impact. | |
| dc.subject.category | Ciencia de Datos | |
| dc.subject.category | Política Pública | |
