EconBase
← All papers

Reconstructing Subnational Labor Indicators in Colombia: An Integrated Machine and Deep Learning Approach

Jaime Vera-Jaramillo

arXiv 17 Aug 2025 · Econometrics

arXiv:2508.12514 · PDF · DOI · OpenAlex · Extracted main text

Abstract

This study proposes a unified multi-stage framework to reconstruct consistent monthly and annual labor indicators for all 33 Colombian departments from 1993 to 2025. The approach integrates temporal disaggregation, time-series splicing and interpolation, statistical learning, and institutional covariates to estimate seven key variables: employment, unemployment, labor force participation (PEA), inactivity, working-age population (PET), total population, and informality rate, including in regions without direct survey coverage. The framework enforces labor accounting identities, scales results to demographic projections, and aligns all estimates with national benchmarks to ensure internal coherence. Validation against official departmental GEIH aggregates and city-level informality data for the 23 metropolitan areas yields in-sample Mean Absolute Percentage Errors (MAPEs) below 2.3% across indicators, confirming strong predictive performance. To our knowledge, this is the first dataset to provide spatially exhaustive and temporally consistent monthly labor measures for Colombia. By incorporating both quantitative and qualitative dimensions of employment, the panel enhances the empirical foundation for analysing long-term labor market dynamics, identifying regional disparities, and designing targeted policy interventions.

Citation extraction

40
references
39
in-text mentions
27
distinct cited
1
self-citations
11,914
main-text words

appendix boundary found by appendix_command · 61% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Organización Internacional del Trabajo (OIT) & Comisión Económica pa… (2022) Guía para la construcción de indicadores laborales comparables en América Latina0.73732100%
2Organisation for Economic Co-operation and Development (OECD (2021) Machine learning and labour economics in developing contexts: A review0.73732100%
3Departamento Administrativo Nacional de Estadística (DANE (2025) Boletín Técnico: Mercado laboral - Mayo 20200.64422100%
4García-Peña, D (2017) Convergencia regional de la informalidad en Colombia: Un enfoque de econometría espacial0.51121100%
5González-Herrera, M (2018) Desagregación temporal de series laborales: Métodos de Denton y Chow-Lin bajo restricciones informativas0.51121100%
6Orozco-Castañeda, M. A., Sánchez-Torres, J. A., & Díaz, C. A (2024) Forecasting unemployment using support vector regression and neural networks with economic indicators and Google Trends0.51121100%
7Pérez-Rosero, J. E., Rodríguez, A. C., & Barón, S (2025) Explainable machine learning for labor market forecasting in Colombia: A Gaussian Process and UMAP approach0.51121100%
8Sánchez, A., & Morales, R (2015) Modelación bayesiana del desempleo en Chile con cobertura incompleta0.51121100%
9Vidal, M., Sierra-Suárez, G., & Cerón, L. A (2024) Indicadores regionales del mercado laboral mediante aprendizaje automático0.51121100%
10van Dijk, M., de Lange, T., van Leeuwen, P., & Debie, P (2022) Occupations on the Map: Using a Super Learner Algorithm to Downscale Labor Statistics0.51121100%

Showing the top 10 of 27 scored citations.