Consumer Credit Risk Models Via Machine-Learning Algorithms

By Amir Ehsan Khandani, Adlar Jeewook Kim, Andrew W. Lo. 2010

854 citations recorded by the source corpus.

Subfields: Accounting, Finance, Economics & Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Accounting

In Finance

In Economics & Operations Research

Citations in the corpus

Counterfactual Fairness (2017, background): “Machine learning has spread to fields as diverse as credit scoring [20], crime prediction [5], and loan assessment [25].”
Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning (2018, background): “, admitting a student to university [101], predicting if a defendant awaiting trial can be released safely [102], modeling consumer credit risk [103].”
Characterizing Fairness Over the Set of Good Models Under Selective Labels (2021, background): “Algorithmic risk assessments are increasingly used to make and inform decisions in a variety of high-stakes settings ranging from health care, the child welfare and criminal justice systems to consumer lending and hiring [1, 2, 3, 4, 5, 6, 7, 8, 9].”
Fairness in Decision-Making - The Causal Explanation Formula (2018, background): “…and statistics have been increasingly applied throughout a wide range of real-world decision-making scenarios, including in healthcare, law enforcement, education, and ﬁnance (Mahoney and Mohen 2007; Brennan, Dieterich, and Ehret 2009; Khandani, Kim, and Lo 2010; Sweeney 2013; Angwin et al. 2016).”
An algorithm for removing sensitive information: Application to race-independent recidivism prediction (2017, methodology): “Statistical and machine learning models are increasingly used to inform high-stakes decisions, including hiring [Hoﬀman et al., 2015], credit scoring [Khandani et al., 2010], and throughout all stages of the criminal justice system.”
Equality of Opportunity in Classification: A Causal Approach (2018, background): “The growing adoption of automated systems based on standard classification algorithms throughout society (including in law enforcement, education, and finance [13, 4, 8, 21, 1]) has raised concerns about potential issues due to unfairness and discrimination.”
A Survey on Distributed Machine Learning (2019, background): “Examples include controlling self-driving cars [23], recognizing speech [8], or predicting consumer behavior [82].”
Fair Algorithms for Clustering (2019, background): “heoretical results suggest. 1 Introduction Many important decisions today are made by machine learning algorithms. These range from showing advertisements to customers [59,31], to awarding home loans [47,56], to predicting recidivism [10,32,27]. It is important to ensure that such algorithms are fai”
Predictably Unequal? The Effects of Machine Learning on Credit Markets (2020, neutral): “When applied to a broad set of covariates, the process allows for the possibility of bins in each covariate as in the Nonlinear Logit model described earlier, but rather than the lender (27)For a more in-depth discussion of tree-based models applied to a default forecasting problem see, for example,”
Infusing domain knowledge in AI-based "black box" models for better explainability with application in bankruptcy prediction (2019, neutral): “pers [16, 17, 20, 23, 24, 26, 28, 31–36, 39, 41–44, 48–51, 55, 56, 59, 62– 67, 71, 73] related to mortgage default/bankruptcy prediction and collected all explanatory variables (i.”
Attenuating Bias in Word Vectors (2019, background): “Word vector embeddings as used in machine learning towards applications which significantly a↵ect people’s lives, such as to assess credit [11], predict crime [4], and other emerging domains such judging loan applications and resumes for jobs or college applications.”
Predicting mortgage default using convolutional neural networks (2018, methodology): “Khandani et al. (2010). However, most existing work relies on heuristic hand-crafted feature design.”
Parallel Physics-Informed Neural Networks via Domain Decomposition (2021, background): “In recent years there has seen a surge of machine learning based techniques applied to many complex systems such as autonomous vehicles [1], speech recognition [2, 3], medical diagnosis [4], consumer preferences [5], etc.”
Explainable AI: A Review of Machine Learning Interpretability Methods (2020, background): “As a result, today, a lot of real-world problems in different domains, stretching from retail and banking [3,4] to medicine and healthcare [5–7], are tackled while using machine learning models.”
Deep Reinforcement Learning: An Overview (2017, neutral): “, 2010), consumer credit risk (Khandani et al., 2010), etc.”
When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness (2017, background): “Today, governments and other organizations make use of it in criminal sentencing [4], predicting where to allocate police officers [3, 16], and to estimate an individual’s risk of failing to pay back a loan [8].”