Financial distress prediction: Regularized sparse-based Random Subspace with ER aggregation rule incorporating textual disclosures

Wang, Gang; Ma, Jingling; Chen, Gang; Chen, Xiaolu

doi:10.1016/j.asoc.2020.106152

Cited by 42 publications

(38 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, there are two approaches to integrate information derived from the disclosure text and quantitative finance ratios. The first way is to directly combine text and financial indicators in the data set [ 4 , 5 , 25 , 26 ]. The latter one is similar to ensemble learning, which reprocesses the separately learned text information and financial information [ 29 ], not prevailing for fusing text in financial distress prediction.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Relevant research proved that text fusion benefits more accurate identification of financial distress [ 4 , 5 , 25 ]. Since all listed companies obey structural rules to disclose annual reports, the majority of textual information is similar to each other except MD&A. MD&A is closely related to financial distress prediction as it offers investors the review of the company's performance as well as the future potential from the perspective of management [ 14 , 25 – 27 ]. Thus, it is reasonable to extract texts from MD&A to represent the nonfinancial information for a supplement.…”

Section: Introductionmentioning

confidence: 99%

“…There are already some paradigms to quantify text. Most related studies utilize bag-of-words method for text representation [ 5 , 13 , 14 , 25 , 28 ]. It means that these studies regard the text as a set of scattered segments or isolated words, counting all the terms according to the dictionary to represent text as word count vectors.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning Based on Hierarchical Self‐Attention for Finance Distress Prediction Incorporating Text

Ruan

Sun

Yao

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

To detect comprehensive clues and provide more accurate forecasting in the early stage of financial distress, in addition to financial indicators, digitalization of lengthy but indispensable textual disclosure, such as Management Discussion and Analysis (MD&A), has been emphasized by researchers. However, most studies divide the long text into words and count words to treat the text as word count vectors, bringing massive invalid information but ignoring meaningful contexts. Aiming to efficiently represent the text of large size, an end-to-end neural networks model based on hierarchical self-attention is proposed in this study after the state-of-the-art pretrained model is introduced for text embedding including contexts. The proposed model has two notable characteristics. First, the hierarchical self-attention only affords the essential content with high weights in word-level and sentence-level and automatically neglects lots of information that has no business with risk prediction, which is suitable for extracting effective parts of the large-scale text. Second, after fine-tuning, the word embedding adapts the specific contexts of samples and conveys the original text expression more accurately without excessive manual operations. Experiments confirm that the addition of text improves the accuracy of financial distress forecasting and the proposed model outperforms benchmark models better at AUC and F2-score. For visualization, the elements in the weight matrix of hierarchical self-attention act as scalers to estimate the importance of each word and sentence. In this way, the “red-flag” statement that implies financial risk is figured out and highlighted in the original text, providing effective references for decision-makers.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Based on Hierarchical Self‐Attention for Finance Distress Prediction Incorporating Text

Ruan

Sun

Yao

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Wang et al [11] had some deviations from the conventional methods that focused on financial ratios only to predict distress disregarding non-financial data. Data from China Security Market Accounting Research Database (CSMARD) was used to build a model that focused on the quality of the non-financial parameters in distress prediction.…”

Section: Empirical Reviewmentioning

confidence: 99%

An Analysis of the Predictors of Financial Distress for Zimbabwe Listed Corporates

Muparuri¹,

Gumbo²

2021

AJPAS

View full text Add to dashboard Cite

This study brings novelty to the area of corporate distress modelling in Zimbabwe by exploring company-specific indicators of corporate distress, unlike most of the previous studies, which used financial performance indicators. Using a binary logistic regression on a time series dataset collated between 2010 and 2017, this study establishes book value, book value per share, average debt to equity and equity per share as very signiﬁcant determinants of corporate distress on the Zimbabwe Stock Exchange (ZSE). Future studies incorporating artificial intelligence and a combination of both the traditional financial ratios and market-based indicators is recommended to expand the scope of the study.

show abstract

“…Among the ST companies surveyed in this article in the past three years, 45% have a history of multiple warnings. Many researches are based on Chinese companies as the research background (Mousavi & Lin, 2020;Wang et al, 2020;Sun et al, 2020), and take listing state as the target variable, but most of them focus on feature expansion and model optimization. However, it has not considered that this mechanism itself will have an impact on financial distress forecasts.…”

Section: Introductionmentioning

confidence: 99%

Financial Distress Prediction: A Novel Data Segmentation Research on Chinese Listed Companies

Zhu

Zhou

et al. 2021

Technological and Economic Development of Economy

View full text Add to dashboard Cite

In the Chinese stock market, the unique special treatment (ST) warning mechanism can signal financial distress for listed companies. In existing studies, classification model has been developed to differentiate the two general listing states. However, this classification model cannot explain the internal changes of each listing state. Considering that the requirement of the withdrawal of ST in the mechanism is relatively loose, we propose a new segmentation approach for Chinese listed companies, which are divided into negative companies and positive companies according to the number of times being labeled ST. Under the framework of data mining, we use financial indicators, non-financial indicators, and time series to build a financial distress prediction model of distinguishing the long-term development of different Chinese listed companies. Through data segmentation, we find that the negative samples have a huge destructive interference on the prediction effect of the total sample. On the contrary, positive companies improve the prediction accuracy in all aspects and the optimal feature set is also different from all companies. The main contribution of the paper is to analyze the internal impact of the deterioration of financial distress prediction in time series and construct an optimization model for positive companies.

show abstract

Financial distress prediction: Regularized sparse-based Random Subspace with ER aggregation rule incorporating textual disclosures

Cited by 42 publications

References 73 publications

Deep Learning Based on Hierarchical Self‐Attention for Finance Distress Prediction Incorporating Text

Deep Learning Based on Hierarchical Self‐Attention for Finance Distress Prediction Incorporating Text

An Analysis of the Predictors of Financial Distress for Zimbabwe Listed Corporates

Financial Distress Prediction: A Novel Data Segmentation Research on Chinese Listed Companies

Contact Info

Product

Resources

About