Projection of the electric vehicle market in Colombia: a Machine Learning-based approach
DOI:
https://doi.org/10.26507/paper.4575Keywords:
Machine learning, Support Vector Machine (SVM), Vehicle fleet projection, Electric vehiclesAbstract
In Colombia, the transportation sector accounts for 49% of CO₂ emissions and 43% of total final energy consumption. To mitigate these impacts and support a transition toward cleaner energy, the country has promoted the adoption of electric vehicle fleets. In recent years, sales of these vehicles have grown significantly, reaching 6 000 units in 2023. This progress has been partly driven by government initiatives aimed at encouraging adoption through public plans and policies. However, uncertainty remains as to whether the current market trend will be sufficient to meet national targets, such as the goal of incorporating 600 000 electric vehicles by 2030.
In this context, analyzing electric vehicle market trends becomes increasingly important. This study proposes the use of a Support Vector Machine (SVM) model to forecast the number of light-duty vehicles and subsequently estimate the market share of electric vehicles within the national fleet for the 2030–2035 period. To do so, historical data and exogenous variables such as Gross Domestic Product (GDP), population, and gasoline prices are used.
The projections generated from this approach support infrastructure planning, help anticipate mobility needs, and address challenges related to energy sustainability and emissions reduction. They also aid in identifying areas for improvement and in designing strategies aligned with international climate commitments.
References
Banco Mundial. (2023). Crecimiento del PIB Alemania. Banco Mundial. https://datos.bancomundial.org/indicador/NY.GDP.MKTP.KD.ZG?locations=CO
BBVA Research. (2025). Situación Automotriz 2025. https://www.bbvaresearch.com/publicaciones/colombia-situacion-automotriz-2025/?utm_source=chatgpt.com
Chisanga, C. B., Phiri, E., & Chinene, V. R. N. (2021). Evaluating APSIM-and-DSSAT-CERES-Maize Models under Rainfed Conditions Using Zambian Rainfed Maize Cultivars. Nitrogen (Switzerland), 2(4), 392–414. https://doi.org/10.3390/nitrogen2040027
Chopra, D., & Khurana, R. (2023). Introduction to Machine Learning with Python. In Introduction to Machine Learning with Python. https://doi.org/10.2174/97898151244221230101
Comisión Económica para América Latina y el Caribe CEPAL. (2022). Proyecciones demográficas | Comisión Económica para América Latina y el Caribe. https://www.cepal.org/es/temas/proyecciones-demograficas
Correa, C., & Di Chiara, L. (2020). Beneficios de la electrificación: Estudio del caso del transporte colectivo eléctrico. BID Nota Técnica No IDB-TN-01958. https://doi.org/10.18235/0002608
de Melo, V. S., Camargo, R. S., Krebel, F., Brunoro, M., Nunes, W. T., Fernandes, M. C., & Nunes, R. B. (2023). Greenhouse Gas Emissions Estimation with Electric Vehicles Penetration in the Brazilian Power Grid. 2023 15th IEEE International Conference on Industry Applications, INDUSCON 2023 - Proceedings, 254–261. https://doi.org/10.1109/INDUSCON58041.2023.10374611
Departamento Admistrativo Nacional de Estadística - DANE. (2022). Encuesta Nacional de Calidad de Vida -ECV- 2022. https://www.dane.gov.co/index.php/estadisticas-por-tema/salud/calidad-de-vida-ecv/encuesta-nacional-de-calidad-de-vida-ecv-2022
FENALCO. (2024). Informe Vehículos Eléctricos e Híbridos Diciembre 2024. https://www.fenalco.com.co/blog/gremial-4/informe-vehiculos-electricos-e-hibridos-diciembre-2024-7756
Fuel Car Magazine. (2024). Fuel Car Magazine. https://fuelcarmagazine.com/
García, J. R. (2021). Avance de la Movilidad Eléctrica en Colombia. https://www.researchgate.net/publication/354294236_Avance_de_la_Movilidad_Electrica_en_Colombia
IEA. (2024). Colombia - Countries & Regions - IEA. Countries & Regions - IEA. https://www.iea.org/countries/colombia/emissions
Informes de Expertos. (2025). Mercado Automotriz en Colombia, Participación 2025-2034. https://www.informesdeexpertos.com/informes/mercado-automotriz-en-colombia?
Jiawei Han, Micheline Kamber, J. P. (2014). Data Mining. Concepts and Techniques, 3rd Edition (The Morgan Kaufmann Series in Data Management Systems). In Proceedings - 2013 International Conference on Machine Intelligence Research and Advancement, ICMIRA 2013. http://www.amazon.co.uk/Data-Mining-Concepts-Techniques-Management/dp/0123814790
Li, R. (2023). New Energy Vehicles Industry Stock Price Prediction Based on ARIMA: Tesla, NIO and BAIC BluePark. BCP Business & Management, 38, 3375–3382. https://doi.org/10.54691/bcpbm.v38i.4310
Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2018a). Statistical and Machine Learning forecasting methods: Concerns and ways forward. PLoS ONE, 13(3), e0194889. https://doi.org/10.1371/journal.pone.0194889
Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2018b). Statistical and Machine Learning forecasting methods: Concerns and ways forward. PLoS ONE, 13(3), e0194889. https://doi.org/10.1371/journal.pone.0194889
MINISTERIO DE AMBIENTE Y DESARROLLO SOSTENIBLE, MINISTERIO DE MINAS Y ENERGÍA, M. D. T. U. D. P. M. E. (2019). Estrategia Nacional De Movilidad Eléctrica. In Unidad de Planeación Minero Energética, Republica de Colombia (Vol. 12, Issue 6). https://www.energia.gob.pa/mdocs-posts/estrategia-nacional-de-movilidad-electrica/%0Ahttps://www.minambiente.gov.co/images/AsuntosambientalesySectorialyUrbana/pdf/Estrategia-Nacional-de-Movilidad-Electrica-enme-minambiente.pdf
Ministerio de Minas y Energía. (2024). Estrategia Nacional para la Infraestructura de Carga para vehículos eléctricos Capítulo 2. Modelos de negocio para infraestructura de carga.
Ministerio de Minas y Energía República de Colombia. (2019). Ley 1964 de 2019. 34 páginas. https://www.suin-juriscol.gov.co/viewDocument.asp?id=30036636
Montgomery, D. C., Peck, E., & Vining, G. (2006). Introduccion al Analisis de Regresion Lineal Tercera Edicion. https://www.academia.edu/42811449/Introduccion_al_Analisis_de_Regresion_Lineal_Tercera_Edicion_Montgomery_Peck_Vining
Müller Klaus, R., Smola, A. J., & Schölkopf, B. (1998). Using Support Vector Machines for Time Series Prediction (pp. 243–253). https://www.researchgate.net/publication/216284731_Using_support_vector_machines_for_time_series_prediction https://doi.org/10.7551/mitpress/1130.003.0019
Pourmatin, M., Moeini-Aghtaie, M., Hassannayebi, E., & Hewitt, E. (2024). Transition to Low-Carbon Vehicle Market: Characterization, System Dynamics Modeling, and Forecasting. Energies, 17(14). https://doi.org/10.3390/en17143525
Unidad de Planeación Minero-Energética (UPME). (2018). Proyección de Precios de los Energéticos. https://www.upme.gov.co/simec/planeacion-energetica/proyeccion-de-precios-de-los-energeticos/
Unidad de Planeación Minero-Energética (UPME). (2022). Plan de acción Indicativo del PROURE 2022-2030. 1–153. https://www1.upme.gov.co/DemandayEficiencia/Documents/PROURE/Documento_PROURE_2022-2030_v4.pdf
Unidad de Planeación Minero-Energética (UPME). (2023). Proyección de la demanda de energía eléctrica y potencia máxima 2023-2037.
Usha, T. M., & Balamurugan, S. A. A. (2016). Seasonal Based Electricity Demand Forecasting Using Time Series Analysis. Circuits and Systems, 07(10), 3320–3328. https://doi.org/10.4236/cs.2016.710283
Wong, T. T. (2015). Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognition, 48(9), 2839–2846. https://doi.org/10.1016/j.patcog.2015.03.009
Zhang, Y., & Yang, Y. (2015). Cross-validation for selecting a model selection procedure. Journal of Econometrics, 187(1), 95–112. https://doi.org/10.1016/j.jeconom.2015.02.006
How to Cite
Downloads
Downloads
Published
Proceeding
Section
License
Copyright (c) 2025 Asociación Colombiana de Facultades de Ingeniería - ACOFI
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
| Article metrics | |
|---|---|
| Abstract views | |
| Galley vies | |
| PDF Views | |
| HTML views | |
| Other views | |
