Risk assessment in social lending via random forests

By Milad Malekipirbazari, Vural Aksakalli. 2015

388 citations recorded by the source corpus.

Social lending has emerged as a viable platform alternative to banks.Widespread adoption depends on better risk attribution to borrowers.A random forest (RF) based method is proposed for identifying good borrowers.Our results indicate RF outperforms traditional credit scoring methods. With the advance of electronic commerce and social platforms, social lending (also known as peer-to-peer lending) has emerged as a viable platform where lenders and borrowers can do business without the help of institutional intermediaries such as banks. Social lending has gained significant momentum recently, with some platforms reaching multi-billion dollar loan circulation in a short amount of time. On the other hand, sustainability and possible widespread adoption of such platforms depend heavily on reliable risk attribution to individual borrowers. For this purpose, we propose a random forest (RF) based classification method for predicting borrower status. Our results on data from the popular social lending platform Lending Club (LC) indicate the RF-based method outperforms the FICO credit scores as well as LC grades in identification of good borrowers.

Subfields: Accounting, Economics and Econometrics, Management Information Systems

How researchers see this paper

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

In Accounting

1. Fanyin Zhou
2. Feng Shen
3. Zhiyong Li
4. Keqin Li
5. Silvia Chiappa
6. Xinyi Hu

In Economics and Econometrics

1. Luca Oneto
2. Fanyin Zhou
3. Feng Shen
4. Zhiyong Li
5. Aldo Pacchiano
6. Keqin Li
7. Heinrich Jiang
8. Silvia Chiappa

In Management Information Systems

1. Silvia Chiappa

Citations in the corpus

• Wasserstein Fair Classification (2019, background): “The increasing use of machine learning in decisionmaking scenarios that have serious implications for individuals and society, such as health care, criminal risk assessment, social services, hiring, financial lending, and online advertising (De Fauw et al., 2018; Dieterich et al., 2016; Eubanks, 201”
• A Causal Bayesian Networks Viewpoint on Fairness (2018, neutral): “…used in a wide range of decision-making scenarios that have serious implications for individuals and society, including financial lending [10, 44], hiring [8, 27], online advertising [26, 38], pretrial and immigration detention [5, 40], child maltreatment screening [13, 45], health care [18,…”
• Fairness in Machine Learning (2020, background): “…used in a wide range of decision-making scenarios that have serious implications for individuals and society, including financial lending [20, 120], hiring [17, 77], online advertising [72, 150], pretrial and immigration detention [10, 158], child maltreatment screening [30, 171], health…”
• Inferring the outcomes of rejected loans: an application of semisupervised clustering (2019, methodology): “Malekipirbazari and Aksakalli (2015) adopted RFs in credit risk assessment and proved its effectiveness when compared with the KNNs, logit and SVMs methods.”