Artículos de investigación

Gestión del talento basada en datos modelado predictivo para decisiones sobrecapital humano en la industria BPO

Vol. 22 Núm. 2 (2026)
Publicado: 2026-05-05
Diego Alejandro Diaz Fonseca
Universidad Distrital Francisco José de Caldas image/svg+xml , Universidad Distrital Francisco José de Caldas
Oswaldo Alberto Romero Villalobos
Universidad Distrital Francisco José de Caldas image/svg+xml , Universidad Distrital Francisco José de Caldas
Julio Barón Velandia
Universidad Distrital Francisco José de Caldas image/svg+xml , Universidad Distrital Francisco José de Caldas

Introducción: Este artículo es producto de la investigación “Modelo de perfilación y selección de personal aplicado al sector BPO en Colombia basado en técnicas de predictive analytics y algoritmos genéticos”, desarrollada en la Universidad Distrital Francisco José de Caldas en el año 2025.
Problema: La organización bajo análisis presentó una deserción temprana de 62.82%, evidenciando altos costos asociados con el reclutamiento, la capacitación y la curva de aprendizaje, lo cual implicaba limitaciones en los procesos tradicionales de reclutamiento.
Objetivo: Diseñar y evaluar un modelo predictivo que identifique a los candidatos con mayor probabilidad de al menos 3 meses de permanencia y determine los atributos más influyentes para dicha retención.
Metodología: Se adoptó un enfoque mixto. Las variables relevantes fueron inicialmente identificadas mediante consulta con profesionales de reclutamiento; posteriormente, se entrenaron modelos de aprendizaje automático sobre 560 registros de contratación. Se aplicaron algoritmos como SVC, Random Forest y KNN. El desbalance de clases fue abordado utilizando SMOTE y el desempeño fue evaluado mediante métricas como exactitud, sensibilidad, especificidad y F1-score.
Resultados: El modelo propuesto redujo la deserción temprana mediante simulación de 62.82% a 4.11%, representando una reducción relativa de 93.6%, junto con ahorros estimados de hasta COP $1B en un trimestre. El modelo SVC se destacó con una especificidad de 94.44%, minimizando contrataciones de alto riesgo.
Conclusiones: Los modelos predictivos en el reclutamiento mejoran significativamente la retención y la optimización de recursos.
Originalidad: El estudio vincula la precisión predictiva con un impacto financiero medible en el sector BPO colombiano.
Limitaciones: No se recolectaron atributos sensibles para prevenir sesgo discriminatorio.

Palabras clave: Aprendizaje automático, BPO, modelos predictivos, recursos humanos, selección de personal

Cómo citar

[1]
D. A. Diaz Fonseca, O. A. Romero Villalobos, y J. Barón Velandia, «Gestión del talento basada en datos: modelado predictivo para decisiones sobrecapital humano en la industria BPO», ing. Solidar, vol. 22, n.º 2, pp. 1–30, may 2026, Accedido: sep. 17, 2026. Disponible en: https://revistas.ucc.edu.co/index.php/in/article/view/5622

[1] S. Malisetty, R. V. Archana, and K. V. Kumari, “Predictive analytics in HR management,” Indian Journal of Public Health Research & Development, vol. 8, no. 3, pp. 115–120, 2017, doi: https://doi.org/10.5958/0976-5506.2017.00238.3.

[2] K. Gopinath and A. Balamurugan, “Human resource analytics: Leveraging machine learning for employee attrition prediction,” in Proc. Int. Working Conf. Transfer and Diffusion of IT, Nagpur, India, Dec. 2023, pp. 137–158, doi: imagehttps://doi.org/10.1007/978-3-031-46594-9_9 (image).

[3] R. Priyanka, K. Ravindran, B. Sankaranarayanan, and M. S. Ali, “Employee attrition prediction using analytics approaches,” Decision Analytics Journal, vol. 6, p. 100192, 2023, doi: https://doi.org/10.1016/j.dajour.2023.100192.

[4] B. Jabir, N. Falih, and K. Rahmani, “HR analytics: A roadmap for decision making—Case study,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 15, no. 2, pp. 979–990, 2019, doi: imagehttps://doi.org/10.11591/ijeecs.v15.i2.pp979-990 (image).

[5] A. Q. Mohammed, “HR analytics: A modern tool in HR for predictive decision making,” Journal of Management, vol. 6, no. 3, pp. 51–63, 2019, doi: imagehttps://doi.org/10.34218/JOM.6.3.2019.007 (image).

[6] G. K. Kaya, S. Ustebay, J. Nixon, C. Pilbeam, and M. Sujan, “Exploring the impact of safety culture on incident reporting: Lessons learned from machine learning analysis of NHS England staff survey and incident data,” Safety Science, vol. 166, p. 106260, 2023, doi: **imagehttps://doi (image).org/10.1016/j.ssci.2023.106260.

[7] D. Pessach, G. Singer, D. Avrahami, H. C. Ben-Gal, E. Shmueli, and I. Ben-Gal, “Employees recruitment: A prescriptive analytics approach via machine learning and mathematical programming,” Decision Support Systems, vol. 134, p. 113290, 2020, doi: imagehttps://doi.org/10.1016/j (image).dss.2020.113290.

[8] J. Simons, S. A. Bhatti, and A. Weller, “Machine learning and the meaning of equal treatment,” in Proc. AAAI/ACM Conf. AI, Ethics, and Society, Virtual Event, USA, 2021, pp. 1–10, doi: https://doi.org/10.1145/3461702.3462533.

[9] J. Thakkar and S. G. Deshmukh, “A review on evolution of business process outsourcing industry,” International Journal of Advance Research and Innovative Ideas in Education, vol. 4, no. 4, pp. 2766–2770, 2018. [Online]. Available: [https://iaeme.com/MasterAdmin/Journal_up-](https://iaeme.com/MasterAdmin/Journal_up-)loads/JOM/VOLUME_6_ISSUE_3/JOM_06_03_007.pdf

[10] L. Aronsson and M. Abrahamsson, “BPO and outsourced software development: A systematic literature review,” Journal of Software: Evolution and Process, vol. 29, no. 7, p. e1872, 2017, doi: imagehttps://doi.org/10.1002/smr.1872 (image).

[11] M. C. Lacity and R. Hirschheim, “The information systems outsourcing bandwagon,” MIT Sloan Management Review, vol. 35, no. 1, pp. 73–86, 1993. [Online]. Available: [https://sloanreview](https://sloanreview).mit.edu/article/the-information-systems-outsourcing-bandwagon/

[12] R. L. Click and T. N. Duening, Business process outsourcing: The competitive advantage. New Jersey, NJ, USA: John Wiley & Sons, 2024. [Online]. Available: [https://vdoc.pub/documents/](https://vdoc.pub/documents/)business-process-outsourcing-the-competitive-advantage-7smgp1oe1h70

[13] N. A. Higuera and B. T. Flórez, “Propuesta de mejoramiento de tecnologías de la información para lograr impacto en el desarrollo de proyectos para el sector BPO comercial en Colombia,” B.S. thesis, Universidad Nacional Abierta y a Distancia, Bogotá, Colombia, 2020. [Online]. Available: imagehttps://repository.unad.edu.co/bitstream/handle/10596/34262/nahiguera.pdf (image)

[14] Cámara de Comercio de Bogotá, “Oportunidades y desafíos del sector BPO en Bogotá–Región,” 2019. [Online]. Available: [https://www.ccb.org.co/Documents/10212/27131/Sector](https://www.ccb.org.co/Documents/10212/27131/Sector)_BPO_2019.pdf

[15] J. Sánchez, H. A. Santana, D. A. Restrepo, and D. A. Malagón, “Análisis descriptivo del impacto de la inteligencia artificial en el sector de contact center en Bogotá,” Universidad EAN, Bogotá, Colombia, 2024. [Online]. Available: [https://repository.universidadean.edu.co/server/api/](https://repository.universidadean.edu.co/server/api/)core/bitstreams/6664d474-c976-476c-a60e-524f828de11b/content

[16] J. Hernández, O. Torres, and M. Molina, “The impact of Industry 4.0 on business process outsourcing: A systematic literature review,” International Journal of Innovation, Creativity and Change, vol. 14, no. 5, pp. 1058–1075, 2020. [Online]. Available: [https://repository.udistrital](https://repository.udistrital).edu.co/server/api/core/bitstreams/9a85b8b7-867f-4b80-8546-84fffea10354/content

[17] L. Rodríguez and E. García, “Implementation of a cybersecurity management system for BPO companies,” International Journal of Cyber-Security and Digital Forensics, vol. 9, no. 1, pp. 51–63, 2020, doi: imagehttps://doi.org/10.17781/P002612 (image).

[18] BPRO, “Asociación Colombiana de BPO,” Feb. 25, 2025. [Online]. Available: [https://www.bpro](https://www.bpro).org/

[19] J. A. Romero and B. R. I. S. A. Sánchez, “Digitalización de la gestión del personal en recursos humanos,” Revista Ciencia Administrativa, 2018. [Online]. Available: [https://openurl](https://openurl).ebsco.com/EPDB%3Agcd%3A2%3A33286658/detailv2?sid=ebsco%3Aplink%3Ascholar&id=ebsco%3Agcd%3A138598854

[20] Z. Kaya and G. B. Yildiz, “Prediction of employee turnover in organizations using machine learning algorithms: A decision-making perspective,” in Proc. Int. Symp. Intelligent Manufacturing and Service Systems, Singapore, 2023, pp. 1–10, doi: imagehttps://doi.org/10.1007/978-981 (image)-99-3126-0_25.

[21] J. R. L. Gumucio, “La selección de personal basada en competencias y su relación con la eficacia organizacional,” Perspectivas, vol. 26, pp. 129–152, 2010. [Online]. Available: http://perspectivas.ucb.edu.bo/index.php/a/article/view/186

[22] N. Folger, P. Brosi, J. Stumpf-Wollersheim, and I. M. Welpe, “Applicant reactions to digital selection methods: A signaling perspective on innovativeness and procedural justice,” Journal of Business and Psychology, pp. 1–23, 2021, doi: imagehttps://doi.org/10.1007/s10869-021-09756-8 (image).

[23] M. F. Gonzalez, W. Liu, L. Shirase, D. L. Tomczak, C. E. Lobbe, R. Justenhoven, and N. R. Martin, “Allying with AI? Reactions toward human-based, AI/ML-based, and augmented hiring processes,” Computers in Human Behavior, vol. 130, p. 107179, 2022, doi: **imagehttps://doi (image).org/10.1016/j.chb.2022.107179.

[24] J. E. Carrillo Tubón and D. M. Cevallos Casasilla, “El rol de la inteligencia artificial en las estrategias de comunicación de marketing digital para empresas del sector de La Floresta,” Universidad Politécnica Salesiana, Quito, Ecuador, 2024. [Online]. Available: [[https://dspace](https://dspace).ups.edu.ec/handle/123456789/28710

[25] J. C. Ponce Gallegos et al., Inteligencia artificial. Iniciativa Latinoamericana de Libros de Texto Abiertos (LATIn), 2014. [Online]. Available: [https://rephip.unr.edu.ar/items/8beb7e66-b](https://rephip.unr.edu.ar/items/8beb7e66-b)c8b-48e1-bd7c-3dbc3dfcceb9

[26] M. F. Gonzalez, J. F. Capman, F. L. Oswald, E. R. Theys, and D. L. Tomczak, “Where’s the IO? Artificial intelligence and machine learning in talent management systems,” Personnel Assessment and Decisions, vol. 5, no. 3, p. 5, 2019, doi: https://doi.org/10.25035/pad.2019.03.002.

[27] E. Mjolsness and D. DeCoste, “Machine learning for science: State of the art and future prospects,” Science, vol. 293, no. 5537, pp. 2051–2055, 2001, doi: https://doi.org/10.1126/science.293.5537.2051.

[28] J. D. Kelleher, B. Mac Namee, and A. D’Arcy, Fundamentals of machine learning for predictive data analytics: Algorithms, worked examples, and case studies. Cambridge, MA, USA: MIT Press, 2020, doi: https://doi.org/10.7551/mitpress/11187.001.0001.

[29] D. Abbott, Applied predictive analytics: Principles and techniques for the professional data analyst. Hoboken, NJ, USA: John Wiley & Sons, 2014, doi: https://doi.org/10.1002/9781118729274.

[30] D. T. Larose, Data mining and predictive analytics. Hoboken, NJ, USA: John Wiley & Sons, 2015, doi: https://doi.org/10.1002/9781118874059.

[31] P. Putra, M. Anam, S. Defit, and A. Yunianta, “Enhancing the decision tree algorithm to improve performance across various datasets,” INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi, vol. 8, no. 2, pp. 200–212, 2024, doi: https://doi.org/10.29407/intensif.v8i2.20814.

[32] F. Buontempo, Genetic algorithms and machine learning for programmers: Create AI models and evolve solutions. Raleigh, NC, USA: The Pragmatic Bookshelf, 2019, doi: https://doi.org/10.16834/pragprog.9781680503128.

[33] E. Wirsansky, Hands-on genetic algorithms with Python: Applying genetic algorithms to solve real-world deep learning and artificial intelligence problems. Birmingham, UK: Packt Publishing, 2020, doi: https://doi.org/10.1201/9780429434099.

[34] O. Kramer, K-nearest neighbors. Berlin, Germany: Springer, 2013, doi: https://doi.org/10.1007/978-3-642-38652-7.

[35] S. M. Mazarei, “Predicting employee turnover using tree-based ensemble learning algorithms,” Signal and Data Processing, vol. 20, no. 3, pp. 73–86, 2023, doi: https://doi.org/10.1007/s42979-023-01913-1.

[36] L. S. Khati and M. Kadariya, “Prediction of health care employee turnover using gradient boosting algorithm,” Journal of Science and Technology, vol. 3, no. 1, pp. 66–73, 2023, doi: https://doi.org/10.3126/jost.v3i1.54053.

[37] M. A. Jafor, M. A. H. Wadud, K. Nur, and M. M. Rahman, “Employee promotion prediction using improved AdaBoost machine learning approach,” AIUB Journal of Science and Engineering, vol. 22, no. 3, pp. 258–266, 2023, doi: https://doi.org/10.53799/ajse.v22i3.681.

[38] O. Peretz, M. Koren, and O. Koren, “Naive Bayes classifier—An ensemble procedure for recall and precision enrichment,” Engineering Applications of Artificial Intelligence, vol. 136, p. 108972, 2024, doi: https://doi.org/10.1016/j.engappai.2024.108972.

[39] E. Ramalakshmi and S. R. Kamidi, “Prediction of employee attrition and analyzing reasons: Using multi-layer perceptron in Spark,” in ICICCT 2019—System Reliability, Quality Control, Safety, Maintenance and Management: Applications to Electrical, Electronics and Computer Science and Engineering, Singapore, 2020, pp. 1–10, doi: https://doi.org/10.1007/978-981-15-7961-5_52.

[40] U. Tiwari, S. Ashwani, A. J. Tripathy, and K. D. Kumar, “A two-stage ensemble approach for analysis of optimizing customer churn with LIME interpretability,” in Proc. IEEE Int. Conf. Computing, Power and Communication Technologies, Greater Noida, India, 2024, pp. 1–10, doi: https://doi.org/10.1109/IC2PCT60068.2024.10486392.

[41] C. Liao, “Employee turnover prediction using machine learning models,” in Proc. Int. Conf. Mechatronics Engineering and Artificial Intelligence, Changsha, 2022, pp. 1–10, doi: https://doi.org/10.1109/ICMEAI54614.2022.00042.

[42] L. M. S. V. Mesa I., “Algoritmos genéticos: Evolución, genética y computación,” Revista Cubana de Computación GIGA, no. 4, pp. 26–33, 1998. [Online]. Available: https://repositorio.puce.edu.ec/server/api/core/bitstreams/904f2cff-5f87-4c0e-a444-09ce4dbb3046/content

[43] U. Murugesan, P. Subramanian, S. Srivastava, and A. Dwivedi, “A study of artificial intelligence impacts on human resource digitalization in Industry 4.0,” Decision Analytics Journal, vol. 7, p. 100249, 2023, doi: https://doi.org/10.1016/j.dajour.2023.100249.

[44] C. I. Pinkas, Age discrimination in hiring practices: A quantitative analysis. Northcentral University, 2018. [Online]. Available: https://www.proquest.com/openview/65e2d0b2dd7b6446d40d55a7b8b3490c/1?pq-origsite=gscholar&cbl=18750

[45] A. L. García-Izquierdo, L. D. Vilela, and S. Moscoso, Employee recruitment, selection, and assessment. New York, NY, USA: Psychology Press, 2015, pp. 9–26, doi: https://doi.org/10.4324/9781315694382.

[46] A. B. Cardona Ramos, La cultura organizacional y su impacto en el desempeño laboral como factor de pertenencia y sentido de lealtad dentro de las organizaciones. IDEA, 2023. [Online]. Available: https://repository.umng.edu.co/items/93bccc92-23d5-4070-a7b6-881c61deca1c

[47] J. Lee, S. B. Kim, Y. Kim, and S. Kim, “Predictive analytics for efficient decision making in personnel selection,” International Journal of Management and Decision Making, vol. 22, no. 1, pp. 106–122, 2023, doi: https://doi.org/10.1504/IJMDM.2023.128742.

[48] S. R. K. Indarapu, S. Vodithala, N. Kumar, S. Kiran, S. N. Reddy, and K. Dorthi, “Exploring human resource management intelligence practices using machine learning models,” The Journal of High Technology Management Research, vol. 34, no. 2, p. 100466, 2023, doi: https://doi.org/10.1016/j.hitech.2023.100466.

[49] I. Muraina, “Ideal dataset splitting ratios in machine learning algorithms: General concerns for data scientists and data analysts,” in Proc. Int. Mardin Artuklu Scientific Research Conf., Lagos, Nigeria, 2022. [Online]. Available: https://www.researchgate.net/profile/Ismail-Muraina/publication/358284895_IDEAL_DATASET_SPLITTING_RATIOS_IN_MACHINE_LEARNING_ALGORITHMS_GENERAL_CONCERNS_FOR_DATA_SCIENTISTS_AND_DATA_ANALYSTS/links/61fb97e711a1090a79cc1a8b/IDEAL-DATASET-SPLITTING-RATIOS-IN-MACHINE-LEARNING-ALGORITHMS-GENERAL-CONCERNS-FOR-DATA-SCIENTISTS-AND-DATA-ANALYSTS.pdf

[50] D. Dablain, B. Krawczyk, and N. V. Chawla, “DeepSMOTE: Fusing deep learning and SMOTE for imbalanced data,” IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 9, pp. 6390–6404, 2022, doi: https://doi.org/10.1109/TNNLS.2021.3136503.

[51] V. Kotu and B. Deshpande, Predictive analytics and data mining: Concepts and practice with RapidMiner. Morgan Kaufmann, 2014, doi: https://doi.org/10.1016/C2012-0-06172-1.

[52] M. Atef, S. E. D., and S. Ouf, “Early prediction of employee turnover using machine learning algorithms,” International Journal of Electrical and Computer Engineering Systems, vol. 13, no. 2, pp. 135–144, 2022, doi: https://doi.org/10.32985/ijeces.13.2.4.

[53] V. J. Recilla, M. R. A. Enonaria, R. J. Florida, J. C. M. Bustillo, C. C. Abalorio, and J. C. Trillo, “Predicting employee turnover through genetic algorithm,” in Proc. Int. Conf. Electronics and Sustainable Communication Systems (ICESC), 2024, pp. 1–10, doi: https://doi.org/10.1109/ICESC60838.2024.10469463.

[54] A. Dudáš, “Graphical representation of data prediction potential: Correlation graphs and correlation chains,” The Visual Computer, vol. 40, pp. 6969–6982, 2024, doi: https://doi.org/10.1007/s00371-024-03263-2.

MÉTRICAS
VISTAS DEL ARTÍCULO: 24
VISTAS DEL PDF: 32