QTIAH-GNN: Quantity and Topology Imbalance-aware Heterogeneous Graph Neural Network for Bankruptcy Prediction

Liu, Yucheng; Gao, Z.; Liu, Xiangyang; Luo, P. W.; Yang, Yang; Xiong, Hui

doi:10.1145/3580305.3599479

Cited by 7 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is noted that, for easier classification tasks, high-efficiency results can be achieved with most class imbalance techniques. Furthermore, a variation in the results shown in the literature is evident, with achieved AUC results ranging from 71.4% [150] to 99.98% [108]. Of course, various types of datasets are analyzed, including private data, stock market data, datasets from different data providers, as well as data from SMEs, etc.…”

Section: Discussionmentioning

confidence: 99%

“…The generative adversarial networks are used to generate synthetic samples in different fields: image generation [147], intrusion attack samples [148], tabular data [149], etc. For example, the authors in [150] firstly used GAN to generate bankruptcy samples. This GAN was used together with heterogeneous graph neural network algorithm, and outperformed undersampling, oversampling, SMOTE, and re-weight techniques, achieving an AUC score of 71.4% for the Tianyancha dataset.…”

Section: Hybrid IImentioning

confidence: 99%

See 1 more Smart Citation

Balancing Techniques for Advanced Financial Distress Detection Using Artificial Intelligence

Kuizinienė,

Krilavičius

2024

Electronics

View full text Add to dashboard Cite

Imbalanced datasets are one of the main issues encountered by artificial intelligence researchers, as machine learning (ML) algorithms can become biased toward the majority class and perform insufficiently on the minority classes. Financial distress (FD) is one of the numerous real-world applications of ML, struggling with this issue. Furthermore, the topic of financial distress holds considerable interest for both academics and practitioners due to the non-determined indicators of condition states. This research focuses on the involvement of balancing techniques according to different FD condition states. Moreover, this research was expanded by implementing ML models and dimensionality reduction techniques. During the course of this study, a Combined FD was constructed using five distinct conditions, ten distinct class balancing techniques, five distinct dimensionality reduction techniques, two features selection strategies, eleven machine learning models, and twelve weighted majority algorithms (WMAs). Results revealed that the highest area under the receiver operating characteristic (ROC) curve (AUC) score was achieved when using the extreme gradient boosting machine (XGBoost) feature selection technique, the experimental max number strategy, the undersampling methods, and the WMA 3.1 weighted majority algorithm (i.e., with categorical boosting (CatBoost), XGBoost, and random forest (RF) having equal voting weights). Moreover, this research has introduced a novel approach for setting the condition states of financial distress, including perspectives from debt and change in employment. These outcomes have been achieved utilizing authentic enterprise data from small and medium Lithuanian enterprises.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Hybrid IImentioning

confidence: 99%

Balancing Techniques for Advanced Financial Distress Detection Using Artificial Intelligence

Kuizinienė,

Krilavičius

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…And TianYanCha is the most important big data platform that can provide big data support to contractors in three aspects: identifying owner's integrity, identifying business risks, and identifying government relations. Liu et al, [24] found that big data can predict business bankruptcies. Wang et al, [25] found in his study that TianYanCha can identify corporate risks.…”

Section: Discussionmentioning

confidence: 99%

The Nexus Between Construction Contract Risk Assessment and Big Data in China

Deng Zihao,

Khoo Terh Jing,

Ha Chin Yee

et al. 2023

ARASET

View full text Add to dashboard Cite

The construction market in China is currently showing an increasing trend in terms of project size, complexity, and technical difficulty. With large initial investments and long capital payback periods, construction projects are vulnerable to the external environment during development and risk control is particularly important. Contracts are at the heart of project management and every step of project development revolves around the content of the contract signed by the contractor. Signing contracts to protect the rights of both parties has become the most effective way of controlling project risk. And with big data technology being rapidly developed and widely used, and the amount of data created and accumulated by the internet growing exponentially, big data has the potential to be used for analysis, forecasting and decision making in the construction industry. The aim of this study is therefore to develop a risk identification list for construction project contracts in China, to score the risks within the list according to their incidence and importance, and to find practical applications of big data technology in contract risk assessment. To achieve this goal, this study used qualitative research and in-depth interviews with experts within the Chinese construction engineering industry. The results of this study form a list of risks in Chinese construction contracts, indicating that late payment and government intervention are the most important risks in Chinese construction contracts. This study also identifies TianYanCha, a commonly used big data enterprise risk identification platform in China, which provides big data support in three areas: evaluating owner integrity, enterprise risk identification, and owner relationship knowledge. At the practical level, this study helps contractors to assess project risks and improve contractual contents during the preparation phase of construction projects, thus improving the success rate of projects. At the theoretical level, this study fills the gap in contractual risk assessment for construction projects in China and provides insights for subsequent risk assessment of construction projects based on the contractor's perspective.

show abstract

WIGNN: An adaptive graph-structured reasoning model for credit default prediction

Yan,

Qu,

Chen

et al. 2025

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

QTIAH-GNN: Quantity and Topology Imbalance-aware Heterogeneous Graph Neural Network for Bankruptcy Prediction

Cited by 7 publications

References 26 publications

Balancing Techniques for Advanced Financial Distress Detection Using Artificial Intelligence

Balancing Techniques for Advanced Financial Distress Detection Using Artificial Intelligence

The Nexus Between Construction Contract Risk Assessment and Big Data in China

WIGNN: An adaptive graph-structured reasoning model for credit default prediction

Contact Info

Product

Resources

About