دانلود رایگان مقاله پیش بینی ورشکستگی برای SMEs با استفاده از داده های ارتباطی

Abstract

Bankruptcy prediction has been a popular and challenging research area for decades. Most prediction models are built using financial figures, stock market data and firm specific variables. We complement such traditional low-dimensional data with high-dimensional data on the company’s directors and managers in the prediction models. This information is used to build a network between small and medium-sized enterprises (SMEs), where two companies are related if they share a director or high-level manager. A smoothed version of the weighted-vote relational neighbour classifier is applied on the network and transforms the relationships between companies into bankruptcy prediction scores, thereby assuming that a company is more likely to file for bankruptcy if one of the related companies in its network has already failed. An ensemble model is built that combines the relational model’s output scores with structured data and is applied on two data sets of Belgian and UK SMEs. We find that the relational model gives improved predictions over a simple financial model when detecting the riskiest firms. The largest performance increase is found when the relational and financial data are combined, confirming the complementary nature of both data types.

6. Conclusion

In this paper, we report the potential of relational data for bankruptcy prediction using two large, real-life SME data sets. We show that linking companies based on their managers/board members adds complementary predictive power to the traditional bankruptcy prediction. The results confirm the large predictive value of relational data and demonstrate that this mostly unused data source should be considered when developing bankruptcy prediction models. The proposed design can be easily implemented by financial institutions and credit rating bureaus as this data source is often already at their disposal. Moreover, the smoothed wvRN does not require large IT infrastructures. The methodology can be extended to different applications in banking, such as loan default prediction, fraud detection and marketing. Additionally, the design can be helpful in B2B commerce for targeted advertising and churn prediction.