An Empirical Comparison of Machine-Learning Methods on Bank Client Credit Assessments

Abstract

Machine learning and artificial intelligence have achieved a human-level performance in many application domains, including image classification, speech recognition and machine translation. However, in the financial domain expert-based credit risk models have still been dominating. Establishing meaningful benchmark and comparisons on machine-learning approaches and human expert-based models is a prerequisite in further introducing novel methods. Therefore, our main goal in this study is to establish a new benchmark using real consumer data and to provide machine-learning approaches that can serve as a baseline on this benchmark. We performed an extensive comparison between the machine-learning approaches and a human expert-based model—FICO credit scoring system—by using a Survey of Consumer Finances (SCF) data. As the SCF data is non-synthetic and consists of a large number of real variables, we applied two variable-selection methods: the first method used hypothesis tests, correlation and random forest-based feature importance measures and the second method was only a random forest-based new approach (NAP), to select the best representative features for effective modelling and to compare them. We then built regression models based on various machine-learning algorithms ranging from logistic regression and support vector machines to an ensemble of gradient boosted trees and deep neural networks. Our results demonstrated that if lending institutions in the 2001s had used their own credit scoring model constructed by machine-learning methods explored in this study, their expected credit losses would have been lower, and they would be more sustainable. In addition, the deep neural networks and XGBoost algorithms trained on the subset selected by NAP achieve the highest area under the curve (AUC) and accuracy, respectively.

Literature Review and Content Analysis: Internet Finance, Green Finance, and Sustainability

“…More researchers agree with the triple bottom line theory of "economy, environment and society", namely sustainable development theory. Also, with the advent of the era of big data, digital finance [29], big data finance [6], supply chain finance [30] and other financial topics [31] have attracted researchers' attention. The emergence of relevant literature indicates that people's interest in this research field is increasing.…”

A Deep Learning Model for Estimation of Patients with Undiagnosed Diabetes

“…All reported p-values are two-sided, and significance was set as a p-value of < 0.05. Logistic regression (LR) can be used to discover a linear relationship between independent variables X and a binary dependent variable Y [27,28]. LR transforms log-odds to probability using the logistic function.…”

“…We used a grid search algorithm to find optimal hyperparameters including a number of layers, hidden nodes, learning rate, batch size, and epoch number. Therefore, we applied Adam's [35] optimization algorithm, which is considered one of the best results and is faster than others [28,36]. To avoid overfitting, we used a dropout regularization technique that can avoid learning spurious features at hidden nodes.…”

The explanation game: a formal framework for interpretable machine learning

“…Perhaps the most popular reason to explain algorithms is their large and growing social impact. ML has been used to help evaluate loan applications (Munkhdalai et al 2019) and student admissions (Waters and Miikkulainen 2014), predict criminal recidivism (Dressel and Farid 2018), and identify military targets (Nasrabadi 2014), to name just a few controversial examples. Failure to properly screen training datasets for biased inputs threatens to automate injustices already present in society (Mittelstadt et al 2016).…”