A hybrid machine learning framework for analyzing human decision-making through learning preferences

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

20 Scopus Citations
View graph of relations



Original languageEnglish
Article number102263
Journal / PublicationOmega (United Kingdom)
Online published13 Apr 2020
Publication statusPublished - Jun 2021


Multiple criteria decision aiding (MCDA) is a family of analytic approaches to depicting the rationale of human decisions. To better interpret the contributions of individual attributes to the decision maker, the conventional MCDA approaches assume that the attributes are monotonic and preference independence. However, the capacity in describing the decision maker's preferences is sacrificed as a result of model simplification. To meet the decision maker's demand for more accurate and interpretable decision models, we propose a novel hybrid method, namely Neural Network-based Multiple Criteria Decision Aiding (NN-MCDA), which combines MCDA model and machine learning to achieve better prediction performance while capturing the relationships between individual attributes and the prediction. NN-MCDA uses a linear component (in an additive form of a set of polynomial functions) to characterize such relationships through providing explicit non-monotonic marginal value functions, and a nonlinear component (in a standard multilayer perceptron form) to capture the implicit high-order interactions among attributes and their complex nonlinear transformations. We demonstrate the effectiveness of NN-MCDA with extensive simulation studies and three real-world datasets. The study sheds light on how to improve the prediction performance of MCDA models using machine learning techniques, and how to enhance the interpretability of machine learning models using MCDA approaches.

Research Area(s)

  • Big data analytics, Business analytics, Decision analysis, Machine learning, Multiple criteria decision analysis, Predictive modeling