Credit default prediction of Chinese real estate listed companies based on explainable machine learning

Yuanyuan Ma, Pingping Zhang, Shaodong Duan and Tianjie Zhang

Finance Research Letters, 2023, vol. 58, issue PA

Abstract: It is essential to accurately forecast the credit default of real estate businesses and provide interpretable analysis. The intrinsic interpretable glass-box model and the post-hoc black-box model are used to predict and explain the credit default status of China's real estate listed businesses. Chinese annual reports, stock bar investor remarks, financial indicators and Distance to Default (DD) are taken into consideration when forecasting credit default. The AdaBoost model and the intrinsic Explainable Boosting Machine (EBM) model are determined to have the best prediction results, respectively. We present the explainable prediction results to clearly understand the ranking of feature importance and the impact on the prediction results.

Keywords: Credit default; MD&A(Management discussion and analysis); Investor sentiment; Explainable boosting machine (EBM) model; Feature importance; AdaBoost model; Distance to default (DD) (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1544612323006773
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:finlet:v:58:y:2023:i:pa:s1544612323006773

DOI: 10.1016/j.frl.2023.104305

Access Statistics for this article

Finance Research Letters is currently edited by R. Gençay

More articles in Finance Research Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().