NORMA eResearch @NCI Library

A Fairness-based Recommender System for Charitable Lending Platform Kiva Using Classification and ϵ-Greedy Policy

Hapek, Krisztina (2021) A Fairness-based Recommender System for Charitable Lending Platform Kiva Using Classification and ϵ-Greedy Policy. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (1MB) | Preview

Abstract

A large portion of the world’s population does not have access to traditional financing through banks and financial institutions, thus they have less opportunities to improve their lives, businesses and to grow. The recent appearance and proliferation of peer-to-peer financing platforms has been offering a solution to this problem in the last over a decade. Among them, Kiva, a charitable online platform attracts well-meaning donors who want to help alleviate poverty. Previous studies into peer-to-peer lending, however, discovered that even charitable online lenders are driven by their preferences and biases, which leaves some groups of people still lacking financing opportunities. This paper proposes a fairness-aware loan recommendation system to diversify charitable loans among a larger group of people. The presented solution is based on the initial classification of loan applications using naïve Bayes and logistic regression classifiers followed by an implementation of the ϵ-greedy policy, which is a simple yet efficient strategy for the multi-armed bandit problem. The results show that in spite of the difficulty in correctly classifying loan applications, the ϵ-greedy strategy could be a viable option for the diversification of loan recommendations.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
H Social Sciences > HG Finance > Credit. Debt. Loans.
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Clara Chan
Date Deposited: 02 Dec 2021 20:01
Last Modified: 02 Dec 2021 20:01
URI: https://norma.ncirl.ie/id/eprint/5165

Actions (login required)

View Item View Item