Explainable Artificial Intelligence in an application in Recommendation Systems
DOI:
https://doi.org/10.46480/esj.8.2.180Keywords:
recommendation system, algorithm, prototype, prediction, machine learning, tendersAbstract
Context: This article focuses on the development of interpretive techniques for a recommendation system based on Artificial Intelligence (AI) applied to public procurement processes. The project seeks not only to implement technical solutions but also to address structural and organizational challenges in procurement, improving efficiency and fairness. Method: The exponential growth of technological dependence in various sectors is highlighted, driven by advances in AI and Machine Learning, and the adoption of Explainable Artificial Intelligence (XAI). Results: The project offers as a result a predictive algorithm for the public procurement process. Unlike traditional AI, XAI balances precision with human interpretability, which is crucial for its application in recommendation systems. Conclusions: This holistic approach aims to improve transparency, trust, and efficiency in supplier selection, addressing capacity and risks of bias in automated decision-making, and highlighting the importance of XAI in creating more ethical and reliable systems.
Downloads
References
Alcarazo, L. O. (2022). Evaluación de modelos de inteligencia artificial explicable. Universidad Autónoma de Madrid.
Cóunago, P. (2021). Sistemas de recomendación basados en contenido.
Fonseca, B., & Cornelio, A. (2022). Sistemas de recomendación híbridos.
Fonseca, B. B. (2021). Sistemas de recomendación.
Gonzalo, A. M. (2022). Evaluación de modelos de inteligencia artificial explicable: Caso de uso con clasificadores de licitaciones públicas a partir de textos [Tesis de maestría, Universidad Politécnica de Madrid].
Hernández, N. B. (2020a). Licitaciones públicas.
Hernández, N. B. (2020b). Transparencia y equidad en las recomendaciones basadas en IA en procesos de licitación pública.
Janiesch, C., Zschech, P., & Heinrich, K. (2021). Machine learning and deep learning. Electronic Markets, 31(3), 685–695. DOI: https://doi.org/10.1007/s12525-021-00475-2
Mimbrera, E. (2021). Inteligencia artificial explicable.
Moreno, V. (2023). Sistemas de recomendación basados en memoria (Nearest Neighbour).
Pathak, S. (2024). La XAI – Explainable Artificial Intelligence.
Portal Compras Públicas. (2023). Sistema Nacional de Contratación Pública. https://www.compraspublicas.gob.ec
Ramírez, J. (2018). Deep learning [Tesis de maestría].
Rojo, P. (2019). Modelo predictivo de análisis de riesgo crediticio usando machine learning en una entidad del sector microfinanciero [Tesis de maestría].
Rubio, G., Charry, P., & Pérez, C. (2022). El machine learning.
SERCOP. (2020). Oficios 2020. Servicio Nacional de Contratación Pública.
SERCOP. (2022). Sistema Nacional de Contratación Pública.
Valenzuela, J., Correa, C., & Rendón, D. (2022). Sistemas de recomendación basados en filtrados colaborativos.
Vaquero, A. (2020). Inteligencia artificial.
Xia, L. (2023). Desarrollo de un sistema de recomendación para una empresa de servicios online [Tesis de maestría].
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Miguel Molina Villacís, María Molina Miranda, Ximena Acaro Chacón, Angel Jiménez Villao , Darla Luna Chiriboga
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors retain the copyright of their articles and are therefore free to share, copy, distribute, perform, and publicly communicate their work on their personal websites or in institutional repositories after its publication in this journal, provided that full bibliographic information is given to acknowledge its original publication.
How to Cite
