Bankruptcy prediction for SMEs using relational data

Autor: Julie Moeyersoms, Marija Stankova, David Martens, Ellen Tobback, Tony Bellotti
Jazyk: angličtina
Rok vydání: 2017
Předmět:
Technology
Information Systems and Management
Economics
Computer science
Relational database
MODELS
02 engineering and technology
Relational data
Computer Science
Artificial Intelligence
CLASSIFICATION
Management Information Systems
FINANCIAL RATIOS
Arts and Humanities (miscellaneous)
0502 economics and business
0202 electrical engineering
electronic engineering
information engineering
Developmental and Educational Psychology
Econometrics
FAILURE
Bankruptcy prediction
Data mining
01 Mathematical Sciences
Computer. Automation
RISK
08 Information And Computing Sciences
Actuarial science
Science & Technology
Computer Science
Information Systems
Ensemble forecasting
Operations Research & Management Science
05 social sciences
SME
Data set
MARKET
Bankruptcy
Computer Science
Relational model
15 Commerce
Management
Tourism And Services
Financial modeling
020201 artificial intelligence & image processing
Stock market
Network analysis
NEURAL-NETWORKS
Mathematics
050203 business & management
Information Systems
Zdroj: Decision support systems
ISSN: 0167-9236
Popis: 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.
Databáze: OpenAIRE
Externí odkaz: