On the combination of graph data for assessing thin-file borrowers' creditworthiness

• URL: http://arxiv.org/abs/2111.13666v1
• Date: Fri, 26 Nov 2021 18:45:23 GMT
• Title: On the combination of graph data for assessing thin-file borrowers' creditworthiness
• Authors: Ricardo Mu\~noz-Cancino, Cristi\'an Bravo, Sebasti\'an A. R\'ios, Manuel Gra\~na
• Abstract summary: We introduce a framework to improve credit scoring models by blending several Graph Representation Learning methods. We validated this framework using a unique dataset that characterizes the relationships and credit history for the entire population of a Latin American country. In Corporate lending, where the gain is much higher, it confirms that evaluating an unbanked company cannot solely consider its features.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The thin-file borrowers are customers for whom a creditworthiness assessment is uncertain due to their lack of credit history; many researchers have used borrowers' relationships and interactions networks in the form of graphs as an alternative data source to address this. Incorporating network data is traditionally made by hand-crafted feature engineering, and lately, the graph neural network has emerged as an alternative, but it still does not improve over the traditional method's performance. Here we introduce a framework to improve credit scoring models by blending several Graph Representation Learning methods: feature engineering, graph embeddings, and graph neural networks. We stacked their outputs to produce a single score in this approach. We validated this framework using a unique multi-source dataset that characterizes the relationships and credit history for the entire population of a Latin American country, applying it to credit risk models, application, and behavior, targeting both individuals and companies. Our results show that the graph representation learning methods should be used as complements, and these should not be seen as self-sufficient methods as is currently done. In terms of AUC and KS, we enhance the statistical performance, outperforming traditional methods. In Corporate lending, where the gain is much higher, it confirms that evaluating an unbanked company cannot solely consider its features. The business ecosystem where these firms interact with their owners, suppliers, customers, and other companies provides novel knowledge that enables financial institutions to enhance their creditworthiness assessment. Our results let us know when and which group to use graph data and what effects on performance to expect. They also show the enormous value of graph data on the unbanked credit scoring problem, principally to help companies' banking.

Related papers

• Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis [50.972595036856035]
  We present a code that successfully replicates results from six popular and recent graph recommendation models. We compare these graph models with traditional collaborative filtering models that historically performed well in offline evaluations. By investigating the information flow from users' neighborhoods, we aim to identify which models are influenced by intrinsic features in the dataset structure.
  arXiv  Detail & Related papers  (2023-08-01T09:31:44Z)
• Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural Networks [62.94317686301643]
  Company financial risk is ubiquitous and early risk assessment for listed companies can avoid considerable losses. Traditional methods mainly focus on the financial statements of companies and lack the complex relationships among them. We propose a novel Hierarchical Graph Neural Network (TH-GNN) for Tribe-style graphs via two levels, with the first level to encode the structure pattern of the tribes with contrastive learning, and the second level to diffuse information based on the inter-tribe relations.
  arXiv  Detail & Related papers  (2023-01-31T09:17:13Z)
• A Graph-Enhanced Click Model for Web Search [67.27218481132185]
  We propose a novel graph-enhanced click model (GraphCM) for web search. We exploit both intra-session and inter-session information for the sparsity and cold-start problems.
  arXiv  Detail & Related papers  (2022-06-17T08:32:43Z)
• Relational Graph Neural Networks for Fraud Detection in a Super-App environment [53.561797148529664]
  We propose a framework of relational graph convolutional networks methods for fraudulent behaviour prevention in the financial services of a Super-App. We use an interpretability algorithm for graph neural networks to determine the most important relations to the classification task of the users. Our results show that there is an added value when considering models that take advantage of the alternative data of the Super-App and the interactions found in their high connectivity.
  arXiv  Detail & Related papers  (2021-07-29T00:02:06Z)
• Enabling Machine Learning Algorithms for Credit Scoring -- Explainable Artificial Intelligence (XAI) methods for clear understanding complex predictive models [2.1723750239223034]
  This paper compares various predictive models (logistic regression, logistic regression with weight of evidence transformations and modern artificial intelligence algorithms) and show that advanced tree based models give best results in prediction of client default. We also show how to boost advanced models using techniques which allow to interpret them and made them more accessible for credit risk practitioners.
  arXiv  Detail & Related papers  (2021-04-14T09:44:04Z)
• Supporting Financial Inclusion with Graph Machine Learning and Super-App Alternative Data [63.942632088208505]
  Super-Apps have changed the way we think about the interactions between users and commerce. This paper investigates how different interactions between users within a Super-App provide a new source of information to predict borrower behavior.
  arXiv  Detail & Related papers  (2021-02-19T15:13:06Z)
• Every Corporation Owns Its Image: Corporate Credit Ratings via Convolutional Neural Networks [2.867517731896504]
  We analyze the performance of traditional machine learning models in predicting corporate credit rating. We propose a novel end-to-end method, Corporate Credit Ratings via Convolutional Neural Networks, CCR-CNN. CCR-CNN outperforms the state-of-the-art methods consistently.
  arXiv  Detail & Related papers  (2020-12-03T01:01:34Z)
• Every Corporation Owns Its Structure: Corporate Credit Ratings via Graph Neural Networks [2.7910505923792637]
  We propose a novel model, Corporate Credit Rating via Graph Neural Networks, CCR-GNN for brevity. We firstly construct individual graphs for each corporation based on self-outer product then use GNN to model the feature interaction explicitly. Experiments conducted on the Chinese public-listed corporate rating dataset, prove that CCR-GNN outperforms the state-of-the-art methods consistently.
  arXiv  Detail & Related papers  (2020-11-27T02:57:14Z)
• A Novel Classification Approach for Credit Scoring based on Gaussian Mixture Models [0.0]
  This paper introduces a new method for credit scoring based on Gaussian Mixture Models. Our algorithm classifies consumers into groups which are labeled as positive or negative. We apply our model with real world databases from Australia, Japan, and Germany.
  arXiv  Detail & Related papers  (2020-10-26T07:34:27Z)
• Super-App Behavioral Patterns in Credit Risk Models: Financial, Statistical and Regulatory Implications [110.54266632357673]
  We present the impact of alternative data that originates from an app-based marketplace, in contrast to traditional bureau data, upon credit scoring models. Our results, validated across two countries, show that these new sources of data are particularly useful for predicting financial behavior in low-wealth and young individuals.
  arXiv  Detail & Related papers  (2020-05-09T01:32:03Z)
• The Value of Big Data for Credit Scoring: Enhancing Financial Inclusion using Mobile Phone Data and Social Network Analytics [6.919243767837341]
  This paper leverages alternative data sources to enhance both statistical and economic model performance. A unique combination of datasets, including call-detail records, credit and debit account information of customers is used. The results have an impact in terms of ethical use of call-detail records, regulatory implications, financial inclusion, as well as data sharing and privacy.
  arXiv  Detail & Related papers  (2020-02-23T16:13:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.