DIEGO ALEJANDRO MANRIQUE CABEZAS

Prof. DIEGO ALEJANDRO MANRIQUE CABEZAS

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 April 2024 in Mineral Economics
Verified
Journal Article
Closed access
PDF file
CCCarlos David Cardona-Arenas
Carlos David Cardona-Arenas
DODaniel Osorio
Daniel Osorio
DCDIEGO ALEJANDRO MANRIQUE CABEZAS
DIEGO ALEJANDRO MANRIQUE CABEZAS

10 May 2025 in Computation
Verified
Journal Article
Open access
PDF file
DPDiego Armando Perez-Rosero
Diego Armando Perez-Rosero
DCDIEGO ALEJANDRO MANRIQUE CABEZAS
DIEGO ALEJANDRO MANRIQUE CABEZAS
JTJenniffer Carolina Triana-Martinez
Jenniffer Carolina Triana-Martinez
AAAndres Marino Alvarez
Andres Marino Alvarez
GCGerman Castellanos-Dominguez
German Castellanos-Dominguez
Addressing unemployment is essential for formulating effective public policies. In particular, socioeconomic and monetary variables serve as essential indicators for anticipating labor market trends, given their strong influence on employment dynamics and economic stability. However, effective unemployment rate prediction requires addressing the non-stationary and non-linear characteristics of labor data. Equally important is the preservation of interpretability in both samples and features to ensure that forecasts can meaningfully inform public decision-making. Here, we provide an explainable framework integrating unsupervised and supervised machine learning to enhance unemployment rate prediction and interpretability. Our approach is threefold: (i) we gather a dataset for Colombian unemployment rate prediction including monetary and socioeconomic variables. (ii) Then, we used a Local Biplot technique from the widely recognized Uniform Manifold Approximation and Projection (UMAP) method along with local affine transformations as an unsupervised representation of non-stationary and non-linear data patterns in a simplified and comprehensible manner. (iii) A Gaussian Processes regressor with kernel-based feature relevance analysis is coupled as a supervised counterpart for both unemployment rate prediction and input feature importance analysis. We demonstrated the effectiveness of our proposed approach through a series of experiments conducted on our customized database focused on unemployment indicators in Colombia. Furthermore, we carried out a comparative analysis between traditional statistical techniques and modern machine learning methods. The results revealed that our framework significantly enhances both clustering and predictive performance, while also emphasizing the importance of input samples and feature selection in driving accurate outcomes.

1 May 2024 in Journal of the Knowledge Economy
Verified
Journal Article
Closed access
PDF file
CACarlos David Cardona Arenas
Carlos David Cardona Arenas
DODaniel Osorio
Daniel Osorio
DCDIEGO ALEJANDRO MANRIQUE CABEZAS
DIEGO ALEJANDRO MANRIQUE CABEZAS

30 March 2023 in Semestre Económico
Verified
Journal Article
Open access
PDF file
NRNicolás Restrepo-Carvajal
Nicolás Restrepo-Carvajal
DADaniel Steven Aguirre-Peña
Daniel Steven Aguirre-Peña
DCDIEGO ALEJANDRO MANRIQUE CABEZAS
DIEGO ALEJANDRO MANRIQUE CABEZAS
CLCarlos Evelio López-Ceballos
Carlos Evelio López-Ceballos
El presente estudio describe la evolución de la productividad multifactorial en el sector manufacturero del Eje Cafetero colombiano (Caldas, Risaralda y Quindío) en el periodo 2005-2019, a través de un panel de microdatos obtenidos de la Encuesta Anual Manufacturera (EAM). Para el cumplimiento del objetivo, se emplea la metodología propuesta para corrección de los sesgos de simultaneidad, empleando la demanda por insumos intermedios como proxy de la productividad y la formación bruta de capital, además de los salarios reales para estimar las funciones de producción por departamentos que componen el eje cafetero. Los resultados sugieren que la productividad en el departamento del Quindío ha tenido un comportamiento desfavorable respecto a Caldas y Risaralda en el ámbito agregado, lo cual puede ser consecuencia de una composición industrial heterogénea entre los departamentos del Eje Cafetero, en donde el valor agregado suele concentrarse en zonas de actividad industrial intensivas en capital físico y humano, como Caldas y Risaralda. Por su parte, los hallazgos en el ámbito de firma muestran que existe un comportamiento disímil entre Caldas, donde las empresas grandes son más productivas, y Quindío, donde la productividad aumenta en empresas más pequeñas; entre tanto, para Risaralda los resultados son congruentes dado el tamaño de la empresa.