A case-based reasoning approach to rate microcredit borrower risk in online Kiva P2P lending model
| Pages | 58-83 |
| Published date | 05 February 2018 |
| Date | 05 February 2018 |
| DOI | https://doi.org/10.1108/DTA-02-2017-0009 |
| Author | Mohammed Jamal Uddin,Giuseppe Vizzari,Stefania Bandini,Mahmood Osman Imam |
| Subject Matter | Library & information science,Librarianship/library management,Library technology,Information behaviour & retrieval,Metadata,Information & knowledge management,Information & communications technology,Internet |
A case-based reasoning approach
to rate microcredit borrower risk
in online Kiva P2P lending model
Mohammed Jamal Uddin
Department of Information Systems and Communications,
University of Milan-Bicocca, Milan, Italy and
Department of Finance, University of Chittagong, Chittagong, Bangladesh
Giuseppe Vizzari and Stefania Bandini
Department of Information Systems and Communications,
University of Milan-Bicocca, Milan, Italy, and
Mahmood Osman Imam
Department of Finance, Dhaka University, Dhaka, Bangladesh
Abstract
Purpose –The purpose of this paper is to discuss the case-based reasoning (CBR) approach to improve
microcredit initiatives by means of providing a borrower risk rating system.
Design/methodology/approach –The CBR approach has been used to consider the Kiva microcredit
system, which provides a characterization (rating) of the risk associated with the field partner supporting the
loan, but not of the specific borrower which would benefit from it. The authors discuss how the combination
of available historical data on loans and their outcomes (structured as a case base) and available knowledge
on how to evaluate the risk associated with a loan request can be used to provide the end users with an
indication of the risk rating associated with a loan request based on similar past situations.
Findings –The adopted approach is applied and evaluated employing a selection of cases from individual
loans. From this perspective, the case base and the codified knowledge about how to evaluate risks associated
with a loan represent two examples of knowledge IT artifacts.
Originality/value –The originality of the work lies in borrower risk rating in online indirect peer-to-peer
microcredit lending platforms. The case base and the codified knowledge are the two contributions in
knowledge IT artifacts.
Keywords Microcredit, Case-based reasoning, Online P2P lending, Borrower risk rating,
Expert-based model, Knowledge artifacts
Paper type Case study
1. Introduction
Microfinance and microcredit are innovative poverty-alleviation instruments, recently
conceived but already effectively implemented to support the creation of income-generating
and sustainable activities in developing countries. Although these initiatives often require
basic and relatively trivial interventions of digitization and automation of activities, the new
technological scenario in which computational approaches are previously available just for
the developed countries represents an interesting area of research not only for disciplines
like economics but also for computer science. In particular, this paper discusses the
possibility to adopt the case-based reasoning (CBR) approach (Aamodt and Plaza, 1994) to
improve microcredit initiatives. More precisely, we will consider the Kiva microcredit
system[1], which provides a characterization (rating) of the risk associated with the field
partner supporting the loan, but not of the specific borrower which would benefit from it.
Being active since 2005, Kiva has gathered and it has also made available abundant data
about its own activities; in principle, it would be therefore possible to apply CBR to
automatically propose the missing risk rating. The problem, however, is that the typical
structure for a case includes a description of the specific problem at hand ( for our situation,
Data Technologies and
Applications
Vol. 52 No. 1, 2018
pp. 58-83
© Emerald PublishingLimited
2514-9288
DOI 10.1108/DTA-02-2017-0009
Received 28 February 2017
Revised 21 June 2017
Accepted 6 July 2017
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/2514-9288.htm
58
DTA
52,1
a description of the borrower, field of activity, field partner, country, and more, which will be
more thoroughly described in Section 6), the proposed solution (the risk rating), and the
outcome (the fact that the money was paid back in time, with delays or that it was lost by
the lender). In the present context, however, past data include a complete (although not
necessarily sufficiently structured) case description and even a very detailed outcome of
loans, but a solution part is missing. To solve this circular dependency (we want to apply the
CBR approach to solve the problem, but we need solutions that we do not have), we devised
an expert rule-driven risk rating system to create an initial set of complete cases, identified
to be sufficiently representative of the overall population of loan requests, and to solve the
“cold boot”problem. From this perspective, the case base[2] and the codified knowledge[3]
about how to evaluate risks associated with a loan represent two examples of knowledge IT
artifacts (Cabitza and Locoro, 2014; Salazar-Torres et al., 2008).
We will present different configurations for expert-based borrower risk assessment,
evaluating them in relationship with historical data. We will show that some of these models
can be very good at characterizing as safe loan requests that were fully repaid but, at the
same time, they would also erroneously rate as good loan requests that were not successful.
On the other hand, other configurations of the expert models can be more cautious, and not
only characterize a smaller portion of the loans that were fully repaid as safe, but also more
frequently correctly provide a bad rating of loans that were not fully repaid. Finally, we will
present an evaluation of the developed CBR system that presents encouraging results,
being able to outperform the expert-based models and in general provide a reasonable
characterization of loan requests. Results of both the expert models and the CBR system will
be discussed and evaluated from an economics standpoint.
The paper breaks down as follows: the following sections will present a state of the art in
microfinance and microcredit sectors, then Section 4 will discuss literature related to CBR
applications to microfinance. Section 5 will introduce Kiva and its workflow, highlighting
where and how the proposed system can be set. Section 6, finally, will describe the overall
approach and the current state of development of the proposed system. Section 7 will
describe the evaluation of both the expert-based models and the developed CBR system.
Conclusions and future developments will end the paper.
2. Microfinance
Microfinance is regarded as an innovative and effective poverty-alleviation tool to help the
unbanked poor people, especially in developing countries, aiming to create income-
generating activities (Amin, 2008; Hamada, 2010; Milana and Ashta, 2012). In developing
countries, economic managers have been challenged by and continue to challenge issues like
employment generation, poverty reduction, and sustainable development that microfinance
is dedicated to deliver. It still works as a critical approach against poverty and financial
exclusion even facing some of its recent crises and the resulting criticism (Isa et al., 2011).
Microfinance provides the underserved poor access to financial services that help alleviate
poverty through encouraging income-generating activities, empowering, and enhancing
security which are the priority programs of World Bank proposed in a set of strategies for
fighting against poverty in 2000 (World Bank Report 2000 on Microfinance, 2000).
Since its beginning in the early 1970s, microfinance has a remarkable performance with
strong growth for which it has been positively acknowledged by the stakeholders from all
corners of the world, and especially by the Nobel Peace Prize award in 2006 presented to
Muhammad Yunus, who is the founder of microcredit model termed as Grameen Bank
(Pompa et al., 2012). Traditionally, the need, small amount of loan without collateral, of the
poor people is not served by the formal financial institutions (FIs). Also, such services are
out of their reach due to the complicated application procedure, high interest rates, and long
admission processing. Making the poor people access to financial services, especially
59
Microcredit
borrower risk
To continue reading
Request your trial