Debt risk analysis of non-financial corporates using two-tier networks

Cao, Yuan; Wu, Desheng Dash; Lei, Li

doi:10.1108/imds-09-2019-0495

Cited by 3 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach has allowed for the systematic analysis of how network structure and bank characteristics affect solvency distress contagion risk in interbank networks [59]. As the economic and financial system becomes more complex, the use of complex networks to study systemic risk and risk contagion has become increasingly important [60].…”

Section: Literature Reviewmentioning

confidence: 99%

A Hybrid Network Analysis and Machine Learning Model for Enhanced Financial Distress Prediction

Kadkhoda,

Amiri

2024

IEEE Access

View full text Add to dashboard Cite

Financial distress prediction is a crucial aspect of financial planning, particularly in the face of emerging uncertainties. This study introduces a novel methodology for predicting financial distress by amalgamating network analysis and machine learning techniques. The approach involves establishing two networks among companies based on their similarity and correlation in key financial indicators. The first network reflects similarity across five features, while the second captures correlation in the most critical feature. Subsequently, seven network-centric features are extracted and integrated into the dataset as new variables. Additionally, community detection algorithms are applied to cluster companies, with the resulting labels added as categorical variables. This process yields a modified dataset comprising both initial and network-based variables. Five classification algorithms are employed to forecast financial distress across three scenarios. Initially, models are trained using only the initial features. In subsequent scenarios, network-centric features from both similarity and correlation networks are incorporated, enhancing the predictive accuracy of machine learning models. Notably, features from the similarity network play a pivotal role in this improvement. The proposed model not only showcases superior predictive capabilities but also offers a holistic understanding of the dynamic interactions among financial entities. The results underscore the efficacy of network-based strategies in refining financial distress prediction models, providing valuable insights for decision-makers.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Hybrid Network Analysis and Machine Learning Model for Enhanced Financial Distress Prediction

Kadkhoda,

Amiri

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…At present, scholars have mainly studied the contagion of counterparty risk from the perspective of traditional finance [5][6][7][8][9][10][11][12]. With the proposed goal of carbon peak and carbon neutrality, green finance has been considered the most important solution [13], and new counterparty risks will be induced in the development of green finance.…”

Section: Introductionmentioning

confidence: 99%

Counterparty Risk Contagion Model of Carbon Quota Based on Asset Price Reduction

et al. 2023

View full text Add to dashboard Cite

Driven by the “double carbon” goal, the sale of financial assets at reduced prices by firms due to carbon emission constraints is bound to aggravate the uncertainty and volatility of carbon trading among firms, and potentially create counterparty risk contagion. In view of this, this paper considers the sensitivity of the transaction of corporate financial assets, the transaction price of carbon quotas, and corporate carbon performance; constructs a network model for the risk contagion of carbon quota counterparties; theoretically discusses the risk formation and infection mechanism of carbon quota counterparties; and calculates and simulates the evolutionary characteristics of the risk contagion of carbon quota counterparties. The main research conclusions are as follows. (1) In the interfirm debt network, the sensitivity to the price of selling the financial asset, the probability of credit risk contagion of carbon quotas among firms, the cumulative proportion of assets sold, and the proportion of rational investors in the financial market exert a decreasing phenomenon on the risk of carbon quota counterparties. In addition, the corporate carbon performance shows a marginal increasing phenomenon. (2) When multiple factors intersect, the proportion of rational investors in the financial market has the greatest influence on the formation of the carbon quota counterparty risk, whereas the effect of corporate carbon performance has the least. Corporate carbon risk awareness has the greatest effect on the risk contagion of carbon quota counterparties, whereas the trading price of the carbon quota has the least influence. In addition, the total score of the interfirm assessment has a great impact on the trend and range of the risk contagion of carbon quota counterparties. (3) Corporate carbon risk awareness and the carbon quota trading price have a marginally decreasing effect on the risk contagion of carbon quota counterparties, and corporate carbon performance and the total score of interfirm assessment have a marginally increasing effect. This study has important theoretical and practical significance for preventing interfirm counterparty risk contagion under the double carbon target.

show abstract

Analysis of Financial Statement and Prewarning of Audit Risks Based on Artificial Neural Network

Yan-xia

2021

International Journal of Circuits, Systems and Signal Processing

View full text Add to dashboard Cite

The marketization of social capital has resulted in frequent audit failures, and financial statement frauds. One of the key steps of auditing is the identification of material misstatement risk of financial statement. However, there is no unified analysis framework or quantitative method for identifying this risk. Therefore, this paper aims to analyze financial statement and prewarn audit risks in an accurate manner. Firstly, the items of financial statement were analyzed in three aspects of the target enterprise: balance statement, income statement, and cash flow statement. Next, the authors probed deep into the core indices of the post audit risk verification and evaluation of the business process, constructed a scientific evaluation index system for audit risks of financial statement, and quantified the 89 tertiary indices, 21 secondary indices, and 3 primary indices. After that, an audit risk prediction model for financial statement was established based on neural network. Experimental results show the effectiveness of the proposed model for audit risk prewarning, and applicable to other tasks of financial auditing.

show abstract

Debt risk analysis of non-financial corporates using two-tier networks

Cited by 3 publications

References 42 publications

A Hybrid Network Analysis and Machine Learning Model for Enhanced Financial Distress Prediction

A Hybrid Network Analysis and Machine Learning Model for Enhanced Financial Distress Prediction

Counterparty Risk Contagion Model of Carbon Quota Based on Asset Price Reduction

Analysis of Financial Statement and Prewarning of Audit Risks Based on Artificial Neural Network

Contact Info

Product

Resources

About