Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research

By Stefan Lessmann, Bart Baesens, Hsin-Vonn Seow, Lyn C. Thomas. 2015

1,486 citations recorded by the source corpus.

Subfields: Accounting, Artificial Intelligence, Health Information Management

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 Artificial Intelligence

In Health Information Management

Citations in the corpus

Ekiden: A Platform for Confidentiality-Preserving, Trustworthy, and Performant Smart Contracts (2018, neutral): “In the credit scoring contract, we trained a model of credit scores based on financial records [11].”
'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions (2018, neutral): “[43, 38, 43, 55, 72]), we settled on the following contexts:”
An up-to-date comparison of state-of-the-art classification algorithms (2017, background): “…ability of the classiﬁer, probability metrics that assess the accuracy of the classiﬁer probability predictions, ordering/rank metrics, and those that assess the correctness of the classiﬁcation algorithm’s categorical predictions ( Caruana & Niculescu-Mizil, 2006; Lessmann et al., 2015 ).”
A deep learning approach for credit scoring using credit default swaps (2017, background): “Lessmann et al. (2015) compare 41 classifiers in terms of six performance measures across eight real-world credit scoring data sets.”
Quantum Computing for Finance: State-of-the-Art and Future Prospects (2020, background): “Banks can estimate the risk level of their customers’ loans by credit scoring which can be formulated as classiﬁcation [67] and/or regression problem based on the rich features of customers, such as, age, salary, historical payment, micro and macro economic indicators and so on (see also [68]).”
Credit scoring model: A combination of genetic programming and deep learning (2016, background): “5] A7 [0, 1] A8 [0, 1] A9 [0, 67] A10 [0, 1] A11 [1, 3] A12 [0, 2000] A13 [1, 100001] Y [1, 2]”
Predicting mortgage default using convolutional neural networks (2018, methodology): “For an overview and comparison of papers, see Garćıa et al. (2014) and Lessmann et al. (2015).”
Data Science of the People , for the People , by the People : A Viewpoint on an Emerging Dichotomy (2015, methodology): “On one hand, we have applications such as medical diagnosis [22], loan approval [32] and prison sentencing [9] in which data-driven predictions are used to support people in making consequential decisions that can have a profound effect on people.”
Online Deep Learning: Growing RBM on the fly (2018, neutral): “Several studies have employed batch machine learning techniques for credit scoring ( [1], [11], [6], [18]).”
A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring (2017, methodology): “According to the study of Nanni and Lumini (2009), and Lessmann et al. (2015), ensemble methods perform better than single AI and statistical methods.”
Predictive Modeling of Customer Repayment for Sustainable Pay-As-You-Go Solar Power in Rural India (2015, background): “The overall accuracy we see is not as high as is achieved in other classification problems related to credit scoring [6] or in other application domains.”
Machine Learning in Banking Risk Management: A Literature Review (2019, methodology): “The bulk of the research appears to be focussed on credit scoring techniques, as seen in the number of papers focussing on this area (Ala’raj and Abbod 2016a; Ala’Raj and Abbod 2016b; Bellotti and Crook 2009; Cao et al. 2013; Van Gestel et al. 2003; Guegan et al. 2018; Huang et al. 2007; Keramati an”
Imbalanced enterprise credit evaluation with DTE-SBD: Decision tree ensemble based on SMOTE and bagging with differentiated sampling rates (2018, background): “overcome the weakness of single classifier, more and more studies focus on constructing ensemble models for enterprise credit evaluation, and find that ensemble methods perform better than the base single classifier approaches [24, 28, 43].”
Quantum computing for finance: Overview and prospects (2018, methodology): “The way this problem is typically dealt with relies on a machine learning method known as classiﬁcation [45].”