共 1 条
Financial distress prediction: Regularized sparse-based Random Subspace with ER aggregation rule incorporating textual disclosures
被引:32
|作者:
Wang, Gang
[1
,2
]
Ma, Jingling
[1
]
Chen, Gang
[3
]
Yang, Ying
[1
,2
]
机构:
[1] Hefei Univ Technol, Sch Management, Hefei 230009, Anhui, Peoples R China
[2] Hefei Univ Technol, Minist Educ, Key Lab Proc Optimizat & Intelligent Decis Making, Hefei, Anhui, Peoples R China
[3] Fudan Univ, Sch Management, Shanghai, Peoples R China
基金:
中国国家自然科学基金;
关键词:
Financial distress prediction;
Random subspace;
Textual disclosures;
Grouping features;
Sparse group lasso;
Evidence reasoning rule;
MAJORITY VOTING COMBINATION;
CHINESE LISTED COMPANIES;
SUPPORT VECTOR MACHINES;
NEURAL-NETWORKS;
BANKRUPTCY PREDICTION;
FEATURE-SELECTION;
DISCRIMINANT-ANALYSIS;
EVALUATING SENTIMENT;
CORPORATE FAILURE;
LEARNING-MODELS;
D O I:
10.1016/j.asoc.2020.106152
中图分类号:
TP18 [人工智能理论];
学科分类号:
081104 ;
0812 ;
0835 ;
1405 ;
摘要:
For the sake of risks management, losses reduction, and costs saving, financial distress prediction (FDP) has attracted extensive attention from various communities including academic researchers, industrial practitioners, and government regulators. In addition to the conventional financial information, the textual disclosures regarding companies have received especial concern nowadays and are demonstrated to be effective for FDP. Ensemble methods have become a prevalent research line in the field of FDP incorporating financial and non-financial features. Feature quality is an important factor determining the accuracy in ensemble, however, traditional ensemble methods integrate these different types of features directly and ignore their grouping structures, hence weakening the feature quality and ultimately deteriorating the prediction accuracy. Moreover, although diversity can be obtained by virtue of the randomness of feature sampling in ensemble, the problem is that such randomness leads to the ambiguities among base classifiers, resulting in that the prediction accuracy of each classifier could not be ensured. Having noted these deficiencies, we propose a novel and robust meta FDP framework, which incorporates the feature regularizing module for identifying discriminatory predictive power of multiple features and the probabilistic fusion module for enhancing the aggregation over base classifiers. To validate our proposed regularized sparse-based Random Subspace with Evidential Reasoning rule (RS2_ER), we conducted extensive experiments on the datasets collected from the China Security Market Accounting Research Database (CSMARD), and the experimental results indicate that the proposed RS2_ER method enables the prediction effectiveness on FDP to be significantly facilitated by dealing with the features grouping property and the ambiguities among base classifiers. (C) 2020 Elsevier B.V. All rights reserved.
引用
收藏
页数:18
相关论文