An artificial intelligence system for predicting customer default in e-commerce

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The growing number of e-commerce orders is leading to increased risk management to prevent default in payment. Default in payment is the failure of a customer to settle a bill within 90 days upon receipt. Frequently, credit scoring (CS) is employed to identify customers’ default probability. CS has been widely studied, and many computational methods have been proposed. The primary aim of this work is to develop a CS model to replace the pre-risk check of the e-commerce risk management system Risk Solution Services (RSS), which is currently one of the most used systems to estimate customers’ default probability. The pre-risk check uses data from the order process and includes exclusion rules and a generic CS model. The new model is supposed to replace the whole pre-risk check and has to work both in isolation and in integration with the RSS main risk check. An application of genetic programming (GP) to CS is presented in this paper. The model was developed on a real-world dataset provided by a well-known German financial solutions company. The dataset contains order requests processed by RSS. The results show that GP outperforms the generic CS model of the pre-risk check in both classification accuracy and profit. GP achieved competitive classificatory accuracy with several state-of-the-art machine learning methods, such as logistic regression, support vector machines and boosted trees. Furthermore, the GP model can be used in combination with the RSS main risk check to create a model with even higher discriminatory power.

Original languageEnglish
Pages (from-to)1-21
Number of pages21
JournalExpert Systems with Applications
Volume104
DOIs
Publication statusPublished - 15 Aug 2018

Fingerprint

Artificial intelligence
Genetic programming
Risk management
Computational methods
Support vector machines
Learning systems
Logistics
Profitability

Keywords

  • Credit scoring
  • Genetic programming
  • Machine learning
  • Optimization
  • Risk management

Cite this

@article{bbb415067fbc4efc923ea0cebf592b09,
title = "An artificial intelligence system for predicting customer default in e-commerce",
abstract = "The growing number of e-commerce orders is leading to increased risk management to prevent default in payment. Default in payment is the failure of a customer to settle a bill within 90 days upon receipt. Frequently, credit scoring (CS) is employed to identify customers’ default probability. CS has been widely studied, and many computational methods have been proposed. The primary aim of this work is to develop a CS model to replace the pre-risk check of the e-commerce risk management system Risk Solution Services (RSS), which is currently one of the most used systems to estimate customers’ default probability. The pre-risk check uses data from the order process and includes exclusion rules and a generic CS model. The new model is supposed to replace the whole pre-risk check and has to work both in isolation and in integration with the RSS main risk check. An application of genetic programming (GP) to CS is presented in this paper. The model was developed on a real-world dataset provided by a well-known German financial solutions company. The dataset contains order requests processed by RSS. The results show that GP outperforms the generic CS model of the pre-risk check in both classification accuracy and profit. GP achieved competitive classificatory accuracy with several state-of-the-art machine learning methods, such as logistic regression, support vector machines and boosted trees. Furthermore, the GP model can be used in combination with the RSS main risk check to create a model with even higher discriminatory power.",
keywords = "Credit scoring, Genetic programming, Machine learning, Optimization, Risk management",
author = "Leonardo Vanneschi and Horn, {David Micha} and Mauro Castelli and Aleš Popovič",
note = "Vanneschi, L., Horn, D. M., Castelli, M., & Popovič, A. (2018). An artificial intelligence system for predicting customer default in e-commerce. Expert Systems with Applications, 104, 1-21. DOI: 10.1016/j.eswa.2018.03.025",
year = "2018",
month = "8",
day = "15",
doi = "10.1016/j.eswa.2018.03.025",
language = "English",
volume = "104",
pages = "1--21",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Science B.V., Amsterdam.",

}

An artificial intelligence system for predicting customer default in e-commerce. / Vanneschi, Leonardo; Horn, David Micha; Castelli, Mauro; Popovič, Aleš.

In: Expert Systems with Applications, Vol. 104, 15.08.2018, p. 1-21.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An artificial intelligence system for predicting customer default in e-commerce

AU - Vanneschi, Leonardo

AU - Horn, David Micha

AU - Castelli, Mauro

AU - Popovič, Aleš

N1 - Vanneschi, L., Horn, D. M., Castelli, M., & Popovič, A. (2018). An artificial intelligence system for predicting customer default in e-commerce. Expert Systems with Applications, 104, 1-21. DOI: 10.1016/j.eswa.2018.03.025

PY - 2018/8/15

Y1 - 2018/8/15

N2 - The growing number of e-commerce orders is leading to increased risk management to prevent default in payment. Default in payment is the failure of a customer to settle a bill within 90 days upon receipt. Frequently, credit scoring (CS) is employed to identify customers’ default probability. CS has been widely studied, and many computational methods have been proposed. The primary aim of this work is to develop a CS model to replace the pre-risk check of the e-commerce risk management system Risk Solution Services (RSS), which is currently one of the most used systems to estimate customers’ default probability. The pre-risk check uses data from the order process and includes exclusion rules and a generic CS model. The new model is supposed to replace the whole pre-risk check and has to work both in isolation and in integration with the RSS main risk check. An application of genetic programming (GP) to CS is presented in this paper. The model was developed on a real-world dataset provided by a well-known German financial solutions company. The dataset contains order requests processed by RSS. The results show that GP outperforms the generic CS model of the pre-risk check in both classification accuracy and profit. GP achieved competitive classificatory accuracy with several state-of-the-art machine learning methods, such as logistic regression, support vector machines and boosted trees. Furthermore, the GP model can be used in combination with the RSS main risk check to create a model with even higher discriminatory power.

AB - The growing number of e-commerce orders is leading to increased risk management to prevent default in payment. Default in payment is the failure of a customer to settle a bill within 90 days upon receipt. Frequently, credit scoring (CS) is employed to identify customers’ default probability. CS has been widely studied, and many computational methods have been proposed. The primary aim of this work is to develop a CS model to replace the pre-risk check of the e-commerce risk management system Risk Solution Services (RSS), which is currently one of the most used systems to estimate customers’ default probability. The pre-risk check uses data from the order process and includes exclusion rules and a generic CS model. The new model is supposed to replace the whole pre-risk check and has to work both in isolation and in integration with the RSS main risk check. An application of genetic programming (GP) to CS is presented in this paper. The model was developed on a real-world dataset provided by a well-known German financial solutions company. The dataset contains order requests processed by RSS. The results show that GP outperforms the generic CS model of the pre-risk check in both classification accuracy and profit. GP achieved competitive classificatory accuracy with several state-of-the-art machine learning methods, such as logistic regression, support vector machines and boosted trees. Furthermore, the GP model can be used in combination with the RSS main risk check to create a model with even higher discriminatory power.

KW - Credit scoring

KW - Genetic programming

KW - Machine learning

KW - Optimization

KW - Risk management

UR - http://www.scopus.com/inward/record.url?scp=85043999337&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2018.03.025

DO - 10.1016/j.eswa.2018.03.025

M3 - Article

VL - 104

SP - 1

EP - 21

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -