Abstract
Machine learning models are high-potential tools that enable prediction in problems incorpo- rating multiple attributes exploiting historical data. Prediction models are applicable in au- tonomous recommending systems development based on acquired datasets. They enable to profit from expert knowledge to support decision-makers in various fields. This paper demon- strates the application of an artificial neural network model named Multi-layer Perceptron (MLP) regressor for rankings prediction based on expert assessments performed in the past with multi- criteria decision analysis methods. The prediction given by the trained model shows high con- vergence with the real ranking. It proves that the MLP regressor has wide possibilities in de- veloping autonomous recommending systems that do not need the active participation of the decision-maker. The developed methodology was applied to predict European countries’ rank- ing regarding clean, affordable, and sustainable energy systems for the public in Sustainable Development Goal 7 (SDG 7).
Paper Type
Full Paper
DOI
10.62036/ISD.2023.43
Neural Network Based Multi-Criteria Ranking Prediction - Sustainability Assessment Case Study
Machine learning models are high-potential tools that enable prediction in problems incorpo- rating multiple attributes exploiting historical data. Prediction models are applicable in au- tonomous recommending systems development based on acquired datasets. They enable to profit from expert knowledge to support decision-makers in various fields. This paper demon- strates the application of an artificial neural network model named Multi-layer Perceptron (MLP) regressor for rankings prediction based on expert assessments performed in the past with multi- criteria decision analysis methods. The prediction given by the trained model shows high con- vergence with the real ranking. It proves that the MLP regressor has wide possibilities in de- veloping autonomous recommending systems that do not need the active participation of the decision-maker. The developed methodology was applied to predict European countries’ rank- ing regarding clean, affordable, and sustainable energy systems for the public in Sustainable Development Goal 7 (SDG 7).
Recommended Citation
Watróbski, J., Baczkiewicz, A., Król, R., & Rudawska, I. (2023). Neural Network Based Multi-Criteria Ranking Prediction - Sustainability Assessment Case Study. In A. R. da Silva, M. M. da Silva, J. Estima, C. Barry, M. Lang, H. Linger, & C. Schneider (Eds.), Information Systems Development, Organizational Aspects and Societal Trends (ISD2023 Proceedings). Lisbon, Portugal: Instituto Superior Técnico. ISBN: 978-989-33-5509-1. https://doi.org/10.62036/ISD.2023.43