Assessment of a failure prediction model in the European energy sector: A multicriteria discrimination approach with a PROMETHEE based classification

This study presents the implementation of a non-parametric multiple criteria decision aiding (MCDA) model, the Multi-group Hierarchy Discrimination (M.H.DIS) model, through the application of an outranking MCDA approach, namely the PROMETHEE II, on a dataset of 114 European unlisted companies operating in the energy sector. Firstly, the M.H.DIS model has been developed following a five-fold cross validation procedure to analyze whether the model explains and replicates a two-group pre-defined classification of companies in the considered sample, provided by Bureau van Dijk's Amadeus database. Since the M.H.DIS method achieves a quite limited satisfactory accuracy in predicting the Amadeus classification in the holdout sample, the PROMETHEE II method has been performed then to provide a benchmark sorting procedure useful for comparison purposes. The analysis indicates that in terms of average accuracy, M.H.DIS model development with the PROMETHEE based classification provides consistently better results than the ones obtained with the Amadeus classification in most of combinations, which have been built with the financial variables covering the main firm's dimensions such as profitability, financial structure, liquidity and turnover. The better results of the proposed model in terms of accuracy rate are also confirmed by the comparison to the most three applied machine-learning methods.

Automated summary

This study implements a non-parametric MCDA model on a dataset of European energy companies, finding that the M.H.DIS model development with the PROMETHEE based classification consistently outperforms other methods in terms of accuracy rate.