A combined approach based on robust PCA to improve bankruptcy forecasting

Abstract

Purpose

Starting from a series of financial ratios analysis, this paper aims to build up two indices which take into account both the firm’s debt level and its sustainability to investigate if and to what extent the proposed indices are able to correctly predict firms’ financial bankruptcy probabilities.

Design/methodology/approach

The research implements a statistical approach (tandem analysis) based on both an original use of principal component analysis (PCA) and logit model.

Findings

The econometric results are compared with those of the popular Altman Z-score for different lengths of the reference period and with more recent classifiers. The empirical evidence would suggest a good performance of the proposed indices which, therefore, could be used as early warning signals of bankruptcy.

Practical implications

The potential application of the model is in the spirit of predicting bankruptcy and aiding companies’ evaluation with respect to going-concern considerations, among others, as the early detection of financial distress facilitates the use of rehabilitation measures.

Originality/value

The construction of the indebtedness indices is based on an original use of Robust PCA for skewed data.

Citation

Succurro, M., Arcuri, G. and Costanzo, G.D. (2019), "A combined approach based on robust PCA to improve bankruptcy forecasting", Review of Accounting and Finance, Vol. 18 No. 2, pp. 296-320. https://doi.org/10.1108/RAF-04-2018-0077