Determinants of Chassis Platform Selection in the Andean Bodywork Industry: A Random Forest Approach
Original Article
Authors
-
Pachacama-Nasimba Pachacama-Nasimba
Carrera de Ingeniería Mecánica, Facultad de Ciencias de la Ingeniería, Universidad Técnica Estatal de Quevedo. Quevedo, Ecuador.
https://orcid.org/0000-0001-6315-6641
-
Santiago Acuña-Hidalgo
Dirección de Regulación del Transporte Terrestre, Tránsito y Seguridad Vial, Agencia Nacional de Regulación y Control del Transporte Terrestre, Tránsito y Seguridad Víal. Quito, Ecuador.
https://orcid.org/0009-0004-5170-4304
-
Paul Lisintuña-Toapanta
Carrera de Mecánica Automotriz, Instituto Superior Tecnológico Ciudad de Valencia. Quevedo, Ecuador.
https://orcid.org/0009-0006-0556-7454
-
Nexar Barreto-Anchundia
Independent researcher. Quevedo, Ecuador.
https://orcid.org/0009-0007-9167-3794
DOI:
https://doi.org/10.33936/riemat.v11i1.8309Keywords:
random forest, chassis selection, bus body manufacturing, vehicle homologation, machine learningAbstract
The Ecuadorian bus body manufacturing industry relies on imported chassis platforms, yet the factors driving their selection remain quantitatively unexplored. This study applies a Random Forest classifier to the National Transit Agency's Body Homologation Registry (n = 1,505 certifications, 2017–2025) to identify the determinants of chassis brand selection among six dominant brands that account for 96.5% of the market. Results reveal that passenger seating capacity is the primary predictor (Mean Decrease in Gini Impurity = 0.534; permutation importance = 0.090), substantially outweighing both service modality and manufacturing city location. The model achieved an overall accuracy of 63.3% (10-fold stratified cross-validation: 63.1% ± 2.6%), suggesting that approximately one-third of the selection decision is governed by commercial factors absent from administrative records, such as acquisition costs and dealer relationships. Distinct capacity-based market niches were identified: Scania dominates the high-capacity long-haul segment, Chevrolet and Volkswagen specialize in urban transit, while HINO operates as a generalist platform commanding 63.1% market share. These findings provide quantitative evidence for strategic procurement decisions and evidence-based industrial policy in the sector.
Downloads
References
Asamblea Nacional del Ecuador. (2014). Ley Orgánica de Transporte Terrestre, Tránsito y Seguridad Vial. https://www.gob.ec/regulaciones
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Cámara de Industrias de Tungurahua. (2022). Informe del Sector Metalmecánico y Carrocero de Tungurahua 2022. https://www.cit.org.ec
Chen, H., Chiang, R. H. L., & Storey, V. C. (2012). Business intelligence and analytics: From big data to big impact. MIS Quarterly: Management Information Systems, 36(4), 1165–1188. https://doi.org/10.2307/41703503
Connelly, R., Playford, C. J., Gayle, V., & Dibben, C. (2016). The role of administrative data in the big data revolution in social science research. Social Science Research, 59, 1–12. https://doi.org/10.1016/j.ssresearch.2016.04.015
Delgado, M., Porter, M. E., & Stern, S. (2016). Defining clusters of related industries. Journal of Economic Geography, 16(1), 1–38. https://doi.org/10.1093/jeg/lbv017
Genuer, R., Poggi, J. M., & Tuleau-Malot, C. (2010). Variable selection using random forests. Pattern Recognition Letters, 31(14), 2225–2236. https://doi.org/10.1016/j.patrec.2010.03.014
Hakim, M. L., Sugiarto, S., Anggraini, R., & Rizky, M. (2023). Determinants of Travel Mode Choice Using Random Forest Classifier: Evidence from Census-Based Household Travel Survey. Transportation Research Interdisciplinary Perspectives, 22, 100960. https://doi.org/10.1016/j.trip.2023.100960
Harron, K., Dibben, C., Boyd, J., Hjern, A., Azimaee, M., Barreto, M. L., & Goldstein, H. (2017). Challenges in administrative data linkage for research. Big Data and Society, 4(2), 1–12. https://doi.org/10.1177/2053951717745678
Holweg, M., & Pil, F. K. (2004). The Second Century. The MIT Press. https://doi.org/10.7551/mitpress/6112.001.0001
Kim, S. (2023). Innovating knowledge and information for a firm-level automobile demand forecast system: A machine learning perspective. Journal of Innovation and Knowledge, 8(2), 100355. https://doi.org/10.1016/j.jik.2023.100355
Mc Grath-Lone, L., Jay, M. A., Blackburn, R., Gordon, E., Zylbersztejn, A., Wiljaars, L., & Gilbert, R. (2022). What makes administrative data “research-ready”? A systematic review and thematic analysis of published literature. International Journal of Population Data Science, 7(1), 1718. https://doi.org/10.23889/IJPDS.V7I1.1718
Moradi-Moghadam, M., Alinezhad, A., & Hosseinzadeh Lotfi, F. (2024). Sustainable Supply Chain Decision-Making in the Automotive Industry: A Data-Driven Approach. Socio-Economic Planning Sciences, 93, 101878. https://doi.org/10.1016/j.seps.2024.101878
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12(85), 2825–2830. https://jmlr.org/papers/v12/pedregosa11a.html
Playford, C. J., Gayle, V., Connelly, R., & Gray, A. J. G. (2016). Administrative social science data: The challenge of reproducible research. Big Data and Society, 3(2), 1–12. https://doi.org/10.1177/2053951716684143
Pojani, D., & Stead, D. (2015). Sustainable urban transport in the developing world: Beyond megacities. Sustainability (Switzerland), 7(6), 7784–7805. https://doi.org/10.3390/su7067784
Porter, M. E. (1998). Clusters and the new economics of competition. Harvard Business Review, 76(6), 77–90.
Ramírez-Camperos, A. M., González-Mendoza, M., & Toloza-Cano, W. (2020). Automotive Supply Chain in Emerging Economies: A Review of Manufacturing Integration Strategies in Latin America. International Journal of Production Economics, 230, 107870. https://doi.org/10.1016/j.ijpe.2020.107870
Schonlau, M., & Zou, R. Y. (2020). The random forest algorithm for statistical learning. Stata Journal, 20(1), 3–29. https://doi.org/10.1177/1536867X20909688
Servicio Ecuatoriano de Normalización. (2009). NTE INEN 1323: Vehículos automotores. Carrocerías metálicas de buses. Requisitos. https://www.normalizacion.gob.ec
Shwartz-Ziv, R., & Armon, A. (2022). Tabular data: Deep learning is not all you need. Information Fusion, 81, 84–90. https://doi.org/10.1016/j.inffus.2021.11.011
Stodden, V., McNutt, M., Bailey, D. H., Deelman, E., Gil, Y., Hanson, B., Heroux, M. A., Ioannidis, J. P. A., & Taufer, M. (2016). Enhancing reproducibility for computational methods. Science, 354(6317), 1240–1241. https://doi.org/10.1126/science.aah6168
Torres, J. L., & Montoya, R. (2019). La industria carrocera en el Ecuador: Análisis de competitividad y cadena de valor. Revista Publicando, 6(21), 45–62.
Usuga-Cadavid, J. P., Lamouri, S., Grabot, B., Forber, R., & Biali, G. (2020). Machine Learning and Data Mining in Manufacturing. Expert Systems with Applications, 166, 114060. https://doi.org/10.1016/j.eswa.2020.114060
Villacrés, E., Naranjo, M., & Mora, C. (2020). Caracterización del clúster carrocero de Tungurahua: Estructura productiva y encadenamientos. Revista Espacios, 41(7), 15–28. https://www.revistaespacios.com
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Víctor Pachacama-Nasimba, Santiago Acuña-Hidalgo, Paul Lisintuña-Toapanta, Nexar Barreto-Anchundia
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
