Machine-learning models for bankruptcy prediction: do industrial variables matter?

IF 1.5 3区经济学 Q2 ECONOMICS

Spatial Economic Analysis Pub Date : 2021-10-07 DOI:10.1080/17421772.2021.1977377

D. Bragoli, C. Ferretti, P. Ganugi, G. Marseguerra, Davide Mezzogori, F. Zammori

引用次数: 10

Abstract

ABSTRACT We provide a predictive model specifically designed for the Italian economy that classifies solvent and insolvent firms one year in advance using the AIDA Bureau van Dijk data set for the period 2007–15. We apply a full battery of bankruptcy forecasting models, including both traditional and more sophisticated machine-learning techniques, and add to the financial ratios used in the literature a set of industrial/regional variables. We find that XGBoost is the best performer, and that industrial/regional variables are important. Moreover, belonging to a district, having a high mark-up and a greater market share diminish bankruptcy probability.

查看原文本刊更多论文

破产预测的机器学习模型：工业变量重要吗？

我们提供了一个专门为意大利经济设计的预测模型，该模型使用2007 - 2015年期间的AIDA局van Dijk数据集提前一年对有偿债能力和资不抵债的公司进行分类。我们应用了一整套破产预测模型，包括传统的和更复杂的机器学习技术，并在文献中使用的财务比率中添加了一组工业/地区变量。我们发现XGBoost是表现最好的，并且行业/区域变量很重要。而且，同属一个地区，利润率高，市场占有率大，降低了企业破产的可能性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Spatial Economic Analysis ECONOMICS-

CiteScore

5.40

自引率

21.70%

发文量

期刊介绍： Spatial Economic Analysis is a pioneering economics journal dedicated to the development of theory and methods in spatial economics, published by two of the world"s leading learned societies in the analysis of spatial economics, the Regional Studies Association and the British and Irish Section of the Regional Science Association International. A spatial perspective has become increasingly relevant to our understanding of economic phenomena, both on the global scale and at the scale of cities and regions. The growth in international trade, the opening up of emerging markets, the restructuring of the world economy along regional lines, and overall strategic and political significance of globalization, have re-emphasised the importance of geographical analysis.