Predicción de la tasa de desempleo en Colombia a través de machine learning interpretable

dc.contributor.advisorCastellanos Domínguez, Germán
dc.contributor.advisorÁlvarez Meza, Andrés Marino
dc.contributor.authorManrique Cabezas , Diego Alejandro
dc.contributor.researchgroupGrupo de Control y Procesamiento Digital de Señales
dc.date.accessioned2026-02-27T13:30:22Z
dc.date.available2026-02-27T13:30:22Z
dc.date.issued2025
dc.descriptiongraficas, tablasspa
dc.description.abstractEl estudio del desempleo y su predicción precisa revisten una importancia crítica para la formulación de políticas públicas efectivas. La tasa de desempleo no solo refleja el estado del mercado laboral, sino que también tiene implicaciones profundas en el crecimiento económico, la distribución del ingreso y la estabilidad social. En economías emergentes como la colombiana, caracterizadas por alta informalidad, disparidades regionales y sensibilidad a los ciclos económicos, comprender las dinámicas del desempleo resulta fundamental para promover un desarrollo sostenible y equitativo. Esta tesis aborda tres problemáticas centrales que dificultan el análisis riguroso del desempleo en Colombia. En primer lugar, la ausencia de bases de datos estructuradas que integren atributos monetarios y socioeconómicos limita la capacidad de modelar el fenómeno con precisión. En segundo lugar, la naturaleza no lineal y no estacionaria de las series temporales asociadas al desempleo exige codificaciones más sofisticadas para capturar patrones complejos. En tercer lugar, se requiere identificar características relevantes que reflejen patrones locales y que, además de ser interpretables, posean capacidad predictiva. En respuesta a estos desafíos, este trabajo propone un marco explicable de aprendizaje automático para la predicción de la tasa de desempleo en Colombia, estructurado en tres etapas: primero, la construcción de un conjunto de datos con información monetaria y socioeconómica, reconociendo las dificultades que impone la naturaleza no estacionaria y no lineal de los datos económicos; segundo, la identificación y análisis de patrones mediante UMAP y Local Biplot, que permiten reducir la dimensionalidad, agrupar observaciones y visualizar la contribución de las variables a través de transformaciones afines locales; y tercero, el modelado predictivo con Procesos Gaussianos, acompañado de un análisis de relevancia supervisado y no-supervisado basado en kernels para determinar la importancia relativa de cada variable. Este enfoque híbrido busca integrar precisión, capacidad de representación y explicabilidad, ofreciendo un aporte tanto a la investigación académica como al diseño de políticas públicas para el país. Los resultados obtenidos en este trabajo evidencian mejoras significativas en la identificación de patrones, la visualización de relaciones entre variables y la precisión de las predicciones, en comparación con métodos tradicionales; introduciendo un marco híbrido explicable para pronosticar la tasa de desempleo en Colombia, combinando el UL-Biplot (UMAP Local Biplot) con una regresión de Proceso Gaussiano (GP). Por su parte, el componente no supervisado reveló estructuras latentes y clústeres asociados a shocks políticos y eventos económicos críticos, destacando la importancia de variables como la participación laboral, los salarios reales y la actividad económica. Paralelamente, el modelo GP superó a enfoques tradicionales (ARIMA, Lasso, ElasticNet, SVR) en precisión y estabilidad, ofreciendo interpretabilidad mediante análisis de relevancia basado en kernels. De este modo, este marco no solo mejora la capacidad predictiva frente a escenarios no lineales e inciertos, sino que también aporta valor para la política pública al anticipar riesgos laborales, mapear patrones económicos y facilitar intervenciones específicas basadas en evidencia. Como trabajo futuro, se propone ampliar los datos con indicadores regionales, explorar modelos probabilísticos de aprendizaje profundo e integrar variables económicas, sociopolíticas y cualitativas para fortalecer la generalización y la utilidad del modelo en la toma de decisiones (Texto tomado de la fuente).spa
dc.description.abstractThe study of unemployment and its accurate prediction are of critical importance for the formulation of effective public policies. The unemployment rate not only reflects the state of the labor market but also has profound implications for economic growth, income distribution, and social stability. In emerging economies such as Colombia, characterized by high informality, regional disparities, and sensitivity to economic cycles, understanding unemployment dynamics is essential to promote sustainable and equitable development. This thesis addresses three central challenges that hinder a rigorous analysis of unemployment in Colombia. First, the absence of structured databases that integrate monetary and socioeconomic attributes limits the capacity to model the phenomenon accurately. Second, the nonlinear and nonstationary nature of the time series associated with unemployment requires more sophisticated encodings to capture complex patterns. Third, it is necessary to identify relevant features that reflect local patterns and that, in addition to being interpretable, possess predictive power. In response to these challenges, this work proposes an explainable machine learning framework for predicting the unemployment rate in Colombia, structured in three stages: first, the construction of a dataset with monetary and socioeconomic information, acknowledging the difficulties imposed by the nonstationary and nonlinear nature of economic data; second, the identification and analysis of patterns through UMAP and Local Biplot, which enable dimensionality reduction, clustering, and visualization of variable contributions through local affine transformations; and third, predictive modeling with Gaussian Processes, complemented by supervised and unsupervised kernel-based relevance analysis to determine the relative importance of each variable. This hybrid approach seeks to integrate accuracy, representational capacity, and explainability, providing a contribution both to academic research and to the design of public policies in the country. The results obtained in this study show significant improvements in pattern identification, visualization of variable relationships, and prediction accuracy compared to traditional methods, introducing a hybrid explainable framework to forecast Colombia’s unemployment rate by combining UL-Biplot (UMAP Local Biplot) with Gaussian Process regression (GP). The unsupervised component revealed latent structures and clusters associated with political shocks and critical economic events, highlighting the importance of variables such as labor force participation, real wages, and economic activity. In parallel, the GP model outperformed traditional approaches (ARIMA, Lasso, ElasticNet, SVR) in precision and stability, while offering interpretability through kernel-based relevance analysis. In this way, the framework not only enhances predictive capacity under nonlinear and uncertain scenarios but also provides value for public policy by anticipating labor market risks, mapping economic patterns, and supporting evidence-based targeted interventions. As future work, the study proposes extending the dataset with regional indicators, exploring probabilistic deep learning models, and integrating economic, sociopolitical, and qualitative variables to strengthen the generalization and usefulness of the model for decision-making.eng
dc.description.curricularareaEléctrica, Electrónica, Automatización Y Telecomunicaciones.Sede Manizales
dc.description.degreelevelMaestría
dc.description.degreenameMagíster en Ingeniería - Automatización Industrial
dc.description.researchareaInteligencia artificial
dc.format.extentxv, 74 páginas
dc.format.mimetypeapplication/pdf
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/89696
dc.language.isospa
dc.publisherUniversidad Nacional de Colombia
dc.publisher.branchUniversidad Nacional de Colombia - Sede Manizales
dc.publisher.facultyFacultad de Ingeniería y Arquitectura
dc.publisher.placeManizales, Colombia
dc.publisher.programManizales - Ingeniería y Arquitectura - Maestría en Ingeniería - Automatización Industrial
dc.relation.indexedAgrosavia
dc.relation.indexedBireme
dc.relation.indexedRedCol
dc.relation.indexedLaReferencia
dc.relation.indexedAgrovoc
dc.relation.referencesAçıkkar, M., & Tokgöz, S. (2025). Improving multi-class classification: scaled extensions of harmonic mean-based adaptive k-nearest neighbors. Applied Intelligence.
dc.relation.referencesAdu, W. K., Appiahene, P., & Afrifa, S. (2023). VAR, ARIMAX and ARIMA models for nowcasting unemployment rate in Ghana using Google trends. Journal of Electrical Systems and Information Technology.
dc.relation.referencesAdvani, B., Sachan, A., Sahu, U., & Pradhan, A. (2024). Forecasting Major Macroeconomic Variables of the Indian Economy. In Modeling Economic Growth in Contemporary India. Emerald Publishing Limited: Bingley, 1-24.
dc.relation.referencesAlaminos, D., Salas, M., & Partal-Ureña, A. (2024). Hybrid ARMA-GARCH-Neural Networks for intraday strategy exploration in high-frequency trading. Pattern Recognition.
dc.relation.referencesAlbornoz, N., Rojas, C., & Santafe, A.-K. (2025). Rural Women’s Leadership Within the Cocoa Production Chain in Tibú, Norte de Santander, Colombia: A Gender Perspective. Agriculture.
dc.relation.referencesAlizamir, M., Wang, M., Adnan-Ikram, R., Kim, S., Ahmed, K., & Heddam, S. (2024). Developing an efficient explainable artificial intelligence approach for accurate reverse osmosis desalination plant performance prediction: application of SHAP analysis. Engineering Applications of Computational Fluid Mechanic.
dc.relation.referencesAmarasinghe, K., Rodolfa, K. T., Lamba, H., & Ghani, R. (2023). Explainable machine learning for public policy: Use cases, gaps, and research directions. Data & Policy.
dc.relation.referencesAoujil, Z., & Hanine, M. (2024). A review on artificial intelligence and behavioral macroeconomics. The Proceedings of the International Conference on Smart City Applications.
dc.relation.referencesAriza, J., & Rejatec, F. (2021). Composición y evolución de la informalidad laboral en Colombia durante el periodo 2009-2019. Apuntes del CENES, 115-148.
dc.relation.referencesAzzollini, L., Sanlitürk, E., Deimantas, y., & Köksal, S. (2025). At Which Level Does Unemployment Affect Political Trust? A Multilevel Analysis Across Europe. Social Indicators Research.
dc.relation.referencesBagrecha, C., Singh, K., Sharma, G., & Saranya, P. B. (2024). Forecasting silver prices: a univariate ARIMA approach and a proposed model for future direction. Mineral Economics.
dc.relation.referencesBandauko, E., & Arku, G. (2025). Navigating political opportunity structures: Street traders’ associations and collective action in politically volatile urban environments. Political Geography.
dc.relation.referencesBello, O. (2024). The role of data analytics in enhancing financial inclusion in emerging economies. International Journal of Developing and Emerging Economie, 90-112.
dc.relation.referencesBerman, A., de-Fine-Licht, K., & Carlsson, V. (2024). Trustworthy AI in the public sector: An empirical analysis of a Swedish labor market decision-support system. Technology in Society.
dc.relation.referencesBlandón, A. (2018). Principales Problemas de la Información sobre Mercado Laboral en Colombia y Requerimientos de las Regiones. Lumina, 15-28.
dc.relation.referencesBoundi-Chraki, F., & Perrotini-Hernández, I. (2024). Revisiting the Classical Theory of Investment: An Empirical Assessment from the European Union. Journal of Quantitative Economics.
dc.relation.referencesButt, S., Raza, A., Siddiqui, R., Saleem, Y., Cook, B., & Khan, H. (2024). Healthcare employment landscape: comparing job markets for professionals in developed and developing countries . Journal of work-applied management, 84-96.
dc.relation.referencesCapello, R., Caragliu, A., & Dellisanti, R. (2024). Integrating digital and global transformations in forecasting regional growth: The MASST5 model. Spatial Economic Analysis.
dc.relation.referencesCapello, R., Caragliu, A., & Dellisanti, R. (2024). ntegrating digital and global transformations in forecasting regional growth: the MASST5 model. Spatial Economic Analysis, 133-160.
dc.relation.referencesCarbonero, F., Davies, J., Ernst, E., Fossen, F., Samaan, D., & Sorgner, A. (2023). The impact of artificial intelligence on labor markets in developing countries: a new method with an illustration for Lao PDR and urban Viet Nam. Journal of Evolutionary Economics, 57-91.
dc.relation.referencesCarrino, L., Farnia, L., & Giove, S. (2024). Measuring Social Inclusion in Europe: a non-additive approach with the expert-preferences of public policy planners. Journal of the Royal Statistical Society Series A: Statistics in American.
dc.relation.referencesChakraborty, T., Chakraborty, A. K., Biswas, M., Banerjee, S., & Bhattacharya, S. (2021). Unemployment rate forecasting: A hybrid approach. Computational Economics, 57(1), 183-201.
dc.relation.referencesChappell-Jr., H., & Keech, W. (1988). The unemployment rate consequences of partisan monetary policies. Southern Economic Journal, 107-122.
dc.relation.referencesChen, X., Kim, M., Lin, C., & Na, H. (2025). Development of per Capita GDP Forecasting Model Using Deep Learning: Including Consumer Goods Index and Unemployment Rate. Sustainability.
dc.relation.referencesChhibber, S., Rajkumar, S., & Dassanayake, S. (2025). Will Artificial Intelligence Reshape the Global Workforce by 2030? A Cross-Sectoral Analysis of Job Displacement and Transformation. Blockchain, Artificial Intelligence, and Future ResearchVol 1, 1-18.
dc.relation.referencesChodorow-Reich, G., Coglianese, J., & Karabarbounis, L. (2019). The macro effects of unemployment benefit extensions: A measurement error approach. Q. J. Econ, 227-279.
dc.relation.referencesCM, J., Hoang, N., & Yarram, S. (2025). Interaction Effect of Economic Globalization and Income per Capita on Unemployment. economies.
dc.relation.referencesCojocaru, R., Bolboasa, M., Agafitei, M., Copca, N., & Stelian, F. (2025). Unveiling Regional Disparities in Unemployment: A Spatial Econometric Study of Spain. Sustainability, 1-17.
dc.relation.referencesComisión Económica para América Latina y el Caribe. (2003). Metodologías para la integración de bases de datos de Encuestas de Hogares. Santiago de Chile: CEPAL.
dc.relation.referencesComisión Económica para América Latina y el Caribe. (2022). Informalidad Laboral en América Latina. Santiago de Chile: CEPAL.
dc.relation.referencesCuberos, M., Albornoz, N., Ramirez, C., & Santafé, A.-K. (2024). Integration of Unemployed Venezuelan Immigrant Women in Colombia. Social sciences.
dc.relation.referencesDa Re, D., Marini, G., Bonannella, C., Laurini, F., Manica, M., Anicic, N., . . . al., e. (2025). Modelling the seasonal dynamics of Aedes albopictus populations using a spatio-temporal stacked machine learning model. Scientific Reports.
dc.relation.referencesDe Soto, H. (1986). El otro sendero. Lima : ILD.
dc.relation.referencesDepartamento Administrativo Nacional de Estadística. (2020). Metodología general de la Gran Encuesta Integrada de Hogares. Bogotá: DANE.
dc.relation.referencesDepartamento Administrativo Nacional de Estadística. (2025). Metodología de Encuestas Económicas y de Empleo. Bogotá D.C: DANE.
dc.relation.referencesDossche, W., Vansteenkiste, S., Baesens, B., & Lemahieu, W. (2024). Interpretable and Accurate Identification of Job Seekers at Risk of Long-Term Unemployment: Explainable ML-Based Profiling. Computer Science.
dc.relation.referencesDrigo, C. (2025). Human Dignity, Poverty and Social Exclusion Challenges for Europe. En Springer, Probing Human Dignity (págs. 75-101). Springer link.
dc.relation.referencesEskandari, H., Saadatmand, H., Ramzan, M., & Mousapour, M. (2024). Innovative framework for accurate and transparent forecasting of energy consumption: A fusion of feature selection and interpretable machine learning. Applied Energy.
dc.relation.referencesFajimi, B. A. (2025). Roles of social workers in bridging the gap between social policy and social action in youth unemployment in Nigeria. . Humanities, 30-46.
dc.relation.referencesFendel, T. (2014). Work-related migration and unemployment. Journal for Labour Market Research, 233-243.
dc.relation.referencesFreiesleben, T., König, G., Molnar, C., & Tejero-Cantero, A. (2024). Scientific inference with interpretable machine learning: Analyzing models to learn about real-world phenomena. Minds and Machines.
dc.relation.referencesGallegati, M., & Gallegati, S. (2025). Why does economics need complexity? Soft Computing.
dc.relation.referencesGarcía, L. (2019). La economía colombiana y la economía mundial. Bogotá: Pontificia Universidad Javeriana.
dc.relation.referencesGhorpade, Y., Franco-Restrepo, C., & Castellanos-Rodriguez, L. (2024). Social protection and labor market policies for the informally employed: a review of evidence from low-and middle-income countries. Social Protection and Jobs Discussion Paper.
dc.relation.referencesGómez, A. (2020). Modelo de máxima verosimilitud. Libre empresa, 121-138.
dc.relation.referencesHasan-Chy, M. K., & Nana-Buadi, O. (2024). Role of Machine Learning in Policy Making and Evaluation. International Journal of Innovative Science and Research Technology.
dc.relation.referencesHeaton, J., goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. The MIT Press, 305-317.
dc.relation.referencesHidalgo-Villota, M. (2024). Business cycles in Colombia: stylized facts. Tendencias.
dc.relation.referencesHouse, D., & Keyser, J. (2016). Foundations of physically based modeling and animation. AK Peters/CRC Press - 659.
dc.relation.referencesHuruta, A. D. (2024). Predicting the unemployment rate using autoregressive integrated moving average. Cogent Business & Management.
dc.relation.referencesHyndman, R., & Athanasopoulos, G. (2018). Forecasting: principles and practice. TEXTS.
dc.relation.referencesJung, J., Wang, Y., & Sanchez-Barrioluengo, M. (2024). A scoping review on graduate employability in an era of 'Technological Unemployment. Higher Education Research & Development.
dc.relation.referencesKhasawneh, R., Hailat, M., AlQudah, A., & Mohammad, A. H. (2025). The dual impact of tax evasion, does tax evasion incentivize or dampen FDI, perspectives from the emerging economies of BRICS and CIVETS blocs? International Journal of Innovative Research and Scientific Studies, 2796-2803.
dc.relation.referencesKim, K. (2025). Unemployment Dynamics Forecasting with Machine Learning Regression Models. Computer Science.
dc.relation.referencesKrishnamurthy, S. H. (2024). A Comprehensive study of applying machine learning algorithms for time series data prediction to the Irish Labour Market Unemployment Rate. Dublin: National College of Ireland.
dc.relation.referencesKrug, G., Drasch, K., & Jungbauer-Gans, M. (2019). The social stigma of unemployment: consequences of stigma consciousness on job search attitudes, behaviour and success. Journal for Labour Market Research, 1-27.
dc.relation.referencesKumar, V. (2024). Economic Growth without Jobs: Understanding the Global Unemployment Crisis. FOCUS: Journal of international business, 22-43.
dc.relation.referencesLai, H., Khan, Y. A., Thaljaoui, A., Chammam, W., & Abbas, S. Z. (2021). COVID-19 pandemic and unemployment rate: A hybrid unemployment rate prediction approach for developed and developing countries of Asia. Soft Computing.
dc.relation.referencesLeishman, C., & Liang, W. (2022). An alternative approach to estimating agglomeration and productivity using geography, demography and evidence from satellite imagery. Regional Studies; Regional Science, 44-65.
dc.relation.referencesLi, X., Wang, Y., Basu, S., Kumbier, K., & Yu, B. (2019). A debiased MDI feature importance measure for random forests. Advances in Neural Information Processing Systems.
dc.relation.referencesLinardatos, P., Papastefanopoulos, V., & Kotsiantis, S. (2020). Explainable ai: A review of machine learning interpretability methods. Entropy.
dc.relation.referencesLiu, H., Ong, Y., Shen, X., & Cai, J. (2020). When Gaussian process meets big data: A review of scalable GPs. IEEE transactions on neural networks and learning systems.
dc.relation.referencesLiu, H., Ong, Y., Shen, X., & Cai, J. (2020). When Gaussian Process Meets Big Data: A Review of Scalable GPs. IEEE Trans. Neural Networks Learn., 4405-4423.
dc.relation.referencesMaldonado, O., & Sanchez, D. (2024). The Challenges for Fair Work in Digital Platforms in Colombia: A Critical Exploration on Embodied Justice and Responsibility. En Springer, Humanistic Management in the gig economy (págs. 183-203). Switzerland.: Springer Nature.
dc.relation.referencesMamo, D., Ayele, E., & Teklu, S. (2024). Modelling and analysis of the impact of corruption on economic growth and unemployment. Operations Research Forum.
dc.relation.referencesMárquez, Y. (2022). Unemployment in the Industry with the Arrival of Robotics in Mexico. En Springer, Studies in Systems, Decision and Control (págs. 145-162). Springer.
dc.relation.referencesMasoud, N. (2025). Artificial intelligence and unemployment dynamics: an econometric analysis in high-income economies. Technological Sustainability.
dc.relation.referencesMendivil-Hernández, P. (2025). Realities of Female Entrepreneurship in the Cultural Sector: The Case of Cundinamarca, Colombia. Journal of ecohumanism.
dc.relation.referencesMeried, E. (2025). Monetary policy and income inequality in Brazil: structural vector autoregressive approach. . Discov Sustain.
dc.relation.referencesMero, K., Salgado, N., Meza, J. P.-D., & Ventura, S. (2024). Unemployment Rate Prediction Using a Hybrid Model of Recurrent Neural Networks and Genetic Algorithms. Applied Sciences, 14(8).
dc.relation.referencesMinisterio de Trabajo. (2020). Política Pública de Vendedores informales. Bogotá: Departamento Nacional de Planeación .
dc.relation.referencesMohamed, A., & Abdi, A. (2024). Exploring the dynamics of inflation, unemployment, and economic growth in Somalia: a VECM analysis. Cogent Economics & Finance.
dc.relation.referencesMolnar, C. (2020). Interpretable machine learning. Lulu. com.
dc.relation.referencesMtiraoui, A. (2024). Interaction between Migration and Economic Growth through Unemployment in the Context of Political Instability in the MENA Region. Inernational journal of economics and financial issues, 204-215.
dc.relation.referencesMurphy, K. (2022). Probabilistic machine learning: an introduction. Cmabridge, MA: MIT Press.
dc.relation.referencesMutascu, M., & Hegerty, S. (2023). Predicting the contribution of artificial intelligence to unemployment rates: an artificial neural network approach. Journal of Economics and Finance.
dc.relation.referencesN Papić-Blagojević, B. S. (2024). Analysis of trends in youth unemployment in the European union: the role and importance of youth entrepreneurship. Entrepreneurship and Development for a Green Resilient Economy.
dc.relation.referencesNaciones Unidas. (2023). world drug report. México: ONU.
dc.relation.referencesNnadi, L. C., Watanobe, Y., Rahman, M. M., & John-Otumu, A. M. (2024). rediction of students’ adaptability using explainable AI in educational machine learning models. Applied Sciences.
dc.relation.referencesNosike, C., & Ojobor, O. (2024). Effects of Government Policies on Recessions: Fiscal and Monetary Policy Impact on Unemployment, Poverty, and Inequality. INTERDISCIPLINARY JOURNAL OF AFRICAN & ASIAN STUDIES (IJAAS).
dc.relation.referencesOchsen, C., & Welsch, H. (2011). The social costs of unemployment: accounting for unemployment duration. Applied Economics, 43(27), 3999-4005.
dc.relation.referencesOlschewski, S., Luckman, A., Mason, A., Ludvig, E., & Konstantinidis, E. (2024). The future of decisions from experience: Connecting real-world decision problems to cognitive processes. Perspectives on Psychological Science.
dc.relation.referencesOnatunji, O., Adeleke, O., & Adejumo, A. (2024). Non-linearity in the Phillips curve: Evidence from Nigeria. African Journal of Economic and Management Studies, 132-144.
dc.relation.referencesOnwuka, C. E. (2021). The impact of fiscal and monetary policy on unemployment rate in Nigeria. SSRN 3959996.
dc.relation.referencesOstermann, K., Eppelsheimer, J., Glaser, N., Haller, P., & Oertel, M. (2022). Geodata in labor market research: trends, potentials and perspectives. Journal for labour market research, 31-49.
dc.relation.referencesOzili, P., & Oladipo, O. (2025). Impact of credit expansion and contraction on unemployment. International Journal of Social Economics.
dc.relation.referencesPapić-Blagojević, N., & Stankov, B. (2024). Analysis of trends in youth unemployment in the European union: the role and importance of youth entrepreneurship. Entrepreneurship and Development for a Green Resilient Economy, 181-204.
dc.relation.referencesPatwa, P., Bhardwaj, M., Guptha, V., Kumari, G., Sharma, S., Pykl, S., . . . Ekbal, A. (2021). Overview of constraint 2021 shared tasks: Detecting english covid-19 fake news and hindi hostile posts. Combating Online Hostile Posts in Regional Languages during Emergency.
dc.relation.referencesPérez, D., Manrique, D., Jennifer Triana, A. Á., & Castellanos, G. (2025). An Explainable Framework Integrating Local Biplots and Gaussian Processes for Unemployment Rate Prediction in Colombia. Computation.
dc.relation.referencesPigazo, F., & Ruiz, M. (2024). Analysis of the Dynamic Relationships Between Industrial and Environmental Factors and Unemployment Rate. An Econometric Approach. Dyna. Energía y sostenibilidad, 1-13.
dc.relation.referencesPokou, F., Sadefo-Kamdem, J., & Benhmad, F. (2024). Hybridization of ARIMA with learning models for forecasting of stock market time series. Computational Economics, 1349-1399.
dc.relation.referencesRamos, F., Martínez, L., Martínez, L., Abreu, R., & Rubio, L. (2025). Mapping e-commerce trends in the USA: a time series and deep learning approach. Journal of Marketing Analytics.
dc.relation.referencesRashid, Z., & Rashid, S. (2024). Political Instability Causes & Affects. Pakistan Journal of Humanities and Social Sciences, 294-303.
dc.relation.referencesRe, D. D., Marini, G., Bonannella, C., Laurini, F., Manica, M., Anicic, N., & Albieri, A. (2025). Modelling the seasonal dynamics of Aedesalbopictus populations using a spatio-temporal stacked machine learning model. Scientific Reports.
dc.relation.referencesRosales, R., Perdomo, J., Morales, C., & Urrego, J. (2010). Fundamentos de econometría intermedia:teoría y aplicaciones. Bogotá D.C: Universidad de los Andes.
dc.relation.referencesRustamova, N. S. (2025). Social protection in developing countries: legal, economic and social trends. Qubahan academic journal, 118-149.
dc.relation.referencesSaâdaoui, F., & Rabbouch, H. (2024). Financial forecasting improvement with LSTM-ARFIMA hybrid models and non-Gaussian distributions. Technological Forecasting and Social Change.
dc.relation.referencesSaâdaoui, F., & Rabbouch, H. (2024). Financial forecasting improvement with LSTM-ARFIMA hybrid models and non-Gaussian distributions. Technological Forecasting and Social Change.
dc.relation.referencesShaker, M., El-Batanouny, H., Abdelsalam, M., & Helmy, Y. (2024). Systematic Review of Machine Learning Approaches in Forecasting Economic Growth and Enhancing Decent Work Opportunities: A Comprehensive Analysis. 2024 6th International Conference on Computing and Informatics (ICCI).
dc.relation.referencesShamsi, M., & Beheshti, S. (2025). Separability and scatteredness (S&S) ratio-based efficient SVM regularization parameter, kernel, and kernel parameter selection. Pattern Analysis and Applications.
dc.relation.referencesShavvalpour, S., Mohseni, R., & Kordtabar Firouzjaei, H. (2024). Analysis of the Asymmetric impact of Oil prices, Exchange rates, and their Uncertainty on Unemployment in Oil-Exporting countries. . Macroeconomics Research Letter.
dc.relation.referencesShi, X., Wang, J., & Zhang, B. (2024). A fuzzy time series forecasting model with both accuracy and interpretability is used to forecast wind power. Applied Energy.
dc.relation.referencesSoltani, A., & Lee, C. (2024). The non-linear dynamics of South Australian regional housing markets: A machine learning approach. Applied Geography.
dc.relation.referencesSoto-Otero, M., & Brown, P. (2024). The rise of the digital labour market: characteristics and implications for the study of education, opportunity and work. Journal of Education and Work.
dc.relation.referencesSow, A., Traore, I., Diallo, T., Traore, M., & Ba, A. (2022). Comparison of Gaussian process regression, partial least squares, random forest and support vector machines for a near infrared calibration of paracetamol samples. Results Chem.
dc.relation.referencesStaiger, D., Stock, J. H., & Watson, M. W. (1997). The NAIRU, unemployment and monetary policy. Journal of economic perspectives, 11(1), 33-49.
dc.relation.referencesSuleiman, F. (2025). Social Justice and Economic Policy: Analyzing the Interplay Between Welfare and Market Forces. The open European Journal of social science, 34-45.
dc.relation.referencesSullivan, M. (2024). Understanding and predicting monetary policy framework choice in developing countries. Economic Modelling.
dc.relation.referencesSumayli, A. (2023). Development of advenced machine learning models for optimization of methyl ester biofuel production flom papaya oil: Gaussian process regression (GPR), multilayer perceptron (MLP) and K-nearest neighbor (KNN) regression models. Arabian Journal of Chemistry.
dc.relation.referencesVovk, V. (2013). Empirical inference. Springer.
dc.relation.referencesWamalwa, R., & Ogechukwu, L. (2024). Savings and Sustainable Economic Growth Nexus: A South African Perspective. Sustainability.
dc.relation.referencesWang, Q., Nguyen, T., Huang, J., & Nguyen, T. (2018). An efficient random forests algorithm for high dimensional data classification. Advances in Data Analysis and Classification.
dc.relation.referencesWarhust, C., Knox, A., & Wrigth, S. (2025). Developing a Standard Measure of Job Quality. Work, Employment and Society, 927-948.
dc.relation.referencesWoan-Lin, B., & Hui-Mei, T. (2024). Economic Impact on Palm Oil Stock Returns in Malaysia, Singapore, and Indonesia: A Nardl Model Analysis. Journal of Sustainability Science and Management.
dc.relation.referencesXu, B., Huang, J., Williams, G., Wang, Q., & Ye, Y. (2012). Classifying very high-dimensional data with random forests built from small subspaces. International Journal of Data Warehousing and Mining (IJDWM).
dc.relation.referencesYadav, A., Bareth, R., Kochar, M., Pazoki, M., & Sehiemy, R. (2024). Gaussian process regression based load forecasting model. IET Generation, Transmission & Distribution, 899-910.
dc.relation.referencesYurtsever, M. (2021). Unemployment rate forecasting: LSTM-GRU hybrid approach. Journal for Labour Market Research.
dc.relation.referencesZamanzadeh, A., Chan, M., Ehsani, M., & Ganjali, M. (2020). nemployment duration, Fiscal and monetary policies, and the output gap: How do the quantile relationships look like? Econ. Model, 613-632.
dc.relation.referencesZong, Z., & Guan, Y. (2025). Big DaAI-Driven Intelligent Data Analytics and Predictive Analysis in Industry 4.0: Transforming Knowledge, Innovation, and Efficiency. Journal of the Knowledge Economy, 864-903.
dc.rights.accessrightsinfo:eu-repo/semantics/openAccess
dc.rights.licenseReconocimiento 4.0 Internacional
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subject.ddc330 - Economía::331 - Economía laboral
dc.subject.proposalDesempleospa
dc.subject.proposalExplicabilidadspa
dc.subject.proposalRegresiónspa
dc.subject.proposalInterpretabilidadspa
dc.subject.proposalUnemploymentspa
dc.subject.proposalMachine learningeng
dc.subject.proposalExplainabilityeng
dc.subject.proposalRegressioneng
dc.subject.proposalInterpretabilityeng
dc.subject.proposalDesempleoeng
dc.subject.unescoEmployment policy
dc.subject.unescoMercado de trabajo
dc.subject.unescoLabour market
dc.subject.unescoPolítica de empleo
dc.subject.unescoEmployment policy
dc.subject.unescoIndicadores socioeconómicos
dc.subject.unescoSocio-economic indicators
dc.titlePredicción de la tasa de desempleo en Colombia a través de machine learning interpretablespa
dc.title.translatedPrediction of the unemployment rate in Colombia through interpretable machine learningeng
dc.typeTrabajo de grado - Maestría
dc.type.coarhttp://purl.org/coar/resource_type/c_bdcc
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.contentText
dc.type.driverinfo:eu-repo/semantics/masterThesis
dc.type.versioninfo:eu-repo/semantics/acceptedVersion
dcterms.audience.professionaldevelopmentBibliotecarios
dcterms.audience.professionaldevelopmentEstudiantes
dcterms.audience.professionaldevelopmentInvestigadores
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
Tesis de Maestría en Ingeniería - Automatización Industrial.pdf
Tamaño:
1.99 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería - Automatización Industrial

Bloque de licencias

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
license.txt
Tamaño:
5.74 KB
Formato:
Item-specific license agreed upon to submission
Descripción: