Predicting corporate credit risk: Network contagion via trade credit.

Claudia Berloco,Emanuele Massaro,Arianna Miola,Gianmarco De Francisci Morales,Hashani Kumarasinghe,Daniele Frassineti,Marco Lamieri,Greta Greco,Shuyi Yang,Stefan Cristian Gherghina

doi:10.1371/journal.pone.0250115

Abstract

Trade credit is a payment extension granted by a selling firm to its customer. Companies typically respond to late payments from their customers by delaying payments to suppliers, thus generating a ripple through the transaction network. Therefore, trade credit is as a potential vehicle of propagation of losses in case of default events. The goal of this work is to leverage information on the trade credit among connected firms to predict imminent defaults of firms. We use a unique dataset of client firms of a major Italian bank to investigate firm bankruptcy between October 2016 to March 2018. We develop a model to capture network spillover effects originating from the supply chain on the probability of default of each firm via a sequential approach: the output of a first model component on single firm features is used in a subsequent model which captures network spillovers. While the first component is the standard econometrics way to predict such dynamics, the network module represents an innovative way to look into the effect of trade credit on default probability. This module looks at the transaction network of the firm, as inferred from the payments transiting via the bank, in order to identify the trade partners of the firm. By using several features extracted from the network of transactions, this model is able to predict a large fraction of the defaults, thus showing the value hidden in the network information. Finally, we merge firm and network features with a machine learning model to create a 'hybrid' model, which improves the recall for the task by almost 20 percentage points over the baseline.

Highlights

The goal of the paper is to shed light on the main determinants of firm distress by focusing on the trade credit channel as a key source of contagion, improving the forecasts of the default probabilities of firms in the short-term
The definition of default of an obligor specified in Article 178 of the CRR includes, inter alia, the days past due criterion for default identification, indications of unlikeliness to pay, conditions for a return to nondefaulted status and treatment of the definition of default in external data), when a firm is past due a loan payment for 90 days or more, given the application of a relative materiality threshold of 5% (following the financial crisis, the European Banking Authority (EBA) has established tighter standards around the definition of default to achieve greater alignment across banks and jurisdictions
We model the interaction among firms as a weighted directed graph G(V, E, w), where V is the set of firms, and E is the set of directed edges (u, v) which represent that a firm u is a customer of the firm v, and its credit risk can spread along the direction of the edge

Summary

Introduction

The goal of the paper is to shed light on the main determinants of firm distress by focusing on the trade credit channel as a key source of contagion, improving the forecasts of the default probabilities of firms in the short-term. We design an ‘hybrid’ network-based early warning system that combines statistical tools with machine learning techniques, leverages a huge dataset of financial transactions, and aims to maximize the out-of sample predictive performance.

Objectives

Methods

Findings

Conclusion