Bank Statements to Network Features: Extracting Features Out of Time Series Using Visibility Graph

• Type: Article in International Conference Proceedings Book
• Date: 2022

Authors

Shaji, N (Author) Other; João Gama (Author) FEP; Rita Ribeiro (Author) FCUP; Gomes, P (Author) Other

Conference proceedings International

Title: Advances in Intelligent Data Analysis XX - 20th International Symposium on Intelligent Data Analysis, IDA 2022, Rennes, France, April 20-22, 2022, Proceedings

Pages: 278-289

Indexing

ISI Web of Knowledge - 1 Citation

Scopus - 1 Citation

Other information

Authenticus ID: P-00W-C11

DOI: 10.1007/978-3-031-01333-1_22

Abstract (EN): Non-traditional data like the applicant¿s bank statement is a significant source for decision-making when granting loans. We find that we can use methods from network science on the applicant¿s bank statements to convert inherent cash flow characteristics to predictors for default prediction in a credit scoring or credit risk assessment model. First, the credit cash flow is extracted from a bank statement and later converted into a visibility graph or network. Afterwards, we use this visibility network to find features that predict the borrowers¿ repayment behaviour. We see that feature selection methods select all the five extracted features. Finally, SMOTE is used to balance the training data. The model using the features from the network and the standard features together is shown having superior performance compared to the model that uses only the standard features, indicating the network features¿ predictive power. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Language: English

Type (Professor's evaluation): Scientific