Analysis of Public Tenders in Ecuador: Application of Explainability Techniques in Machine Learning Models

Authors

  • Maria Fernanda Molina Miranda Universidad de Guayaquil, Facultad de Ciencias Matemáticas y Físicas, Ecuador https://orcid.org/0000-0002-4237-4364
  • Ángel Cuenca Ortega Universidad de Guayaquil
  • Luis Espín Pazmiño Universidad de Guayaquil, Facultad de Ciencias Matemáticas y Físicas, Ecuador
  • Miguel Molina Villacís Universidad de Guayaquil, Facultad de Ciencias Matemáticas y Físicas, Ecuador

DOI:

https://doi.org/10.35290/ro.v6n1.2025.1497

Keywords:

tenders, decisión making, algorithms, SHAP, feature importance

Abstract

Public tenders allow institutions to contract goods, works, and services essential for the country’s growth. This work consists of analyzing public tender processes in Ecuador through the application of machine learning techniques and model explainability to improve decision-making. An open dataset extracted from the SERCOP database was collected and processed to identify patterns and key variables that influence the success of tenders. Using classification models such as Random Forest, AdaBoost, and CatBoost, along with explainability techniques like SHAP and Feature Importance, predictive models were developed to transparently understand the decisions generated by the algorithms. The results show that CatBoost was the model with the highest predictive accuracy, and Feature Importance proved to be the most effective technique for explaining the predictions. Furthermore, a web interface was created to input data and determine whether it is advisable for a company to participate in a tender. Explainable artificial intelligence not only improves accuracy but also provides valuable insights for companies to optimize their participation in these processes.

Downloads

Download data is not yet available.

References

Anwar, K., Siddiqui, J., y Saquib, S. (2020). Machine learning-based book recommender system: a survey and new perspectives. International Journal of Intelligent Information and Database Systems, 13(2-4), 231-248. https://doi.org/10.1504/IJIIDS.2020.109457

Arena, S., Florian, E., Sgarbossa, F., Sølvsberg, E., y Zennaro, I. (2024). A conceptual framework for machine lear- ning algorithm selection for predictive maintenance. Engineering Applications of Artificial Intelligence, 133. https://doi.org/10.1016/j.engappai.2024.108340

García, M., Rodríguez, V., Ballesteros, P., Love, P., y Signor, R. (2022). Collusion detection in public procurement auctions with machine learning algorithms. Automation in Construction, 133. https://doi.org/10.1016/j. autcon.2021.104047

Gohel, P., Singh, P., y Mohanty, M. (2021). Explainable AI: current status and future directions. Arxiv. https://doi. org/10.48550/arXiv.2107.07045

Guida, M., Caniato, F., Moretto, A., y Ronchi, S. (2023). The role of artificial intelligence in the procurement pro- cess: State of the art and research agenda. Journal of Purchasing and Supply Management, 29(2). https:// doi.org/10.1016/j.pursup.2023.100823

Love, P., Fang, W., Matthews, J., Porter, S., Luo, H., y Ding, L. (2023). Explainable artificial intelligence (XAI): Precepts, models, and opportunities for research in construction. Advanced Engineering Informatics, 57. https://doi.org/10.1016/j.aei.2023.102024

Molina, M., Acaro, X., Molina, M., Quinoñez, M., Alvarez, G., y Fernandez, J. (2023). Application of explainable artificial intelligence to analyze basic features of a tender. Actas de International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2023 (pp. 1-6). España. 10.1109/ ICECCME57830.2023.10253063

Nai, R., Meo, R., Morina, G., y Pasteris, P. (2023). Public tenders, complaints, machine learning and recommen- der systems: a case study in public administration. Computer Law & Security Review, 51. https://doi.or- g/10.1016/j.clsr.2023.105887

Oussaleh, A. y Azmani, A. (2023). Smart Sourcing Framework for Public Procurement Announcements Using Machine Learning Models. International Conference on Advanced Intelligent Systems for Sustainable Deve- lopment, 637, 921-932. https://doi.org/10.1007/978-3-031-26384-2_83

Pita, C. (2021). Proyecto de Sistema de Recomendación de Filtrado Colaborativo basado en Machine Learning.

Revista PGI(8), 48-51. https://ojs.umsa.bo/ojs/index.php/inf_fcpn_pgi/article/view/46

Riyad, B. y Laila, E. (2024). The Artificial Intelligence and Public Procurement. Actas de 2024 IEEE 15th Interna- tional Colloquium of Logistics and Supply Chain Management (LOGISTIQUA), (pp. 1-6). Tunisia. 10.1109/ LOGISTIQUA61063.2024.10571429

Rojas, E. (2020). Machine Learning: análisis de lenguajes de programación y herramientas para desarrollo. Revis- ta Ibérica de Sistemas e Tecnologias de Informação,(28), 586-599. https://www.proquest.com/openview/ c7e24c997199215aa26a39107dd2fe98/1?pq-origsite=gscholar&cbl=1006393

Rosales, C., Mango, P., Turpo, O., Miranda, V., y Aranda, Á. (2024). El análisis exploratorio de datos: una oportu- nidad para desarrollar competencias STEM/STEAM. Revista Ibérica de Sistemas e Tecnologias de Infor- mação, (70), 87-104. https://dialnet.unirioja.es/servlet/articulo?codigo=9886356

Salem, A., Eyupoglu, S., y Ma’aitah, M. (2024). The Influence of Machine Learning on Enhancing Rational Deci- sion-Making and Trust Levels in e-Government. Systems, 12(9). https://doi.org/10.3390/systems12090373

Sisa, G. (2022). Propuestas para mejorar la contratación e inclusión de las pequeñas y medianas empresas en el sistema de contratación pública del Ecuador [Tesis de posgrado, Universidad Andina Simón Bolívar]. Re- positorio Institucional. https://repositorio.uasb.edu.ec/bitstream/10644/8550/1/T3734-MDACP-Sisa-Pro- puestas.pdf#page=53.20

Published

2025-02-10

How to Cite

Molina Miranda, M. F., Cuenca Ortega, Ángel, Espín Pazmiño, L., & Molina Villacís, M. (2025). Analysis of Public Tenders in Ecuador: Application of Explainability Techniques in Machine Learning Models. ODIGOS JOURNAL, 6(1), 83–100. https://doi.org/10.35290/ro.v6n1.2025.1497

Issue

Section

Articles