2021
DOI: 10.3390/risks9030050
|View full text |Cite
|
Sign up to set email alerts
|

A Machine Learning Approach for Micro-Credit Scoring

Abstract: In micro-lending markets, lack of recorded credit history is a significant impediment to assessing individual borrowers’ creditworthiness and therefore deciding fair interest rates. This research compares various machine learning algorithms on real micro-lending data to test their efficacy at classifying borrowers into various credit categories. We demonstrate that off-the-shelf multi-class classifiers such as random forest algorithms can perform this task very well, using readily available data about customer… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
14
0
1

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 37 publications
(15 citation statements)
references
References 39 publications
0
14
0
1
Order By: Relevance
“…Mobile Microlearning. In the era of "Internet +," the Internet is becoming more and more popular, and mobile intelligent terminals such as smart phones and tablet computers allow us to use the Internet to obtain and transmit information anytime, anywhere, and become a new mode of information acquisition[15]. Mobile microlearning is the continuous development of new mobile technology, a microlearning model that facilitates learning with the aid of mobile terminals.…”
mentioning
confidence: 99%
“…Mobile Microlearning. In the era of "Internet +," the Internet is becoming more and more popular, and mobile intelligent terminals such as smart phones and tablet computers allow us to use the Internet to obtain and transmit information anytime, anywhere, and become a new mode of information acquisition[15]. Mobile microlearning is the continuous development of new mobile technology, a microlearning model that facilitates learning with the aid of mobile terminals.…”
mentioning
confidence: 99%
“…The ROC curve along a 45• angle is equivalent to a random classifier. On the other hand, the closer the AUC is to 1, the machine learning system approaches perfect behaviour [25]. The micro-average measure is a weighted average that accounts for each risk class's contribution.…”
Section: Metricsmentioning
confidence: 99%
“…Furthermore, works such as [46] examine various machine learning algorithms to classify borrowers into various credit categories. However, the authors had to rebalance the dataset using a SMOTENC algorithm.…”
Section: A Additional Related Workmentioning
confidence: 99%