A Comparative Analysis of Machine Learning Models for the Prediction of Insurance Uptake in Kenya

The role of insurance in financial inclusion and economic growth, in general, is immense and is increasingly being recognized. However, low uptake impedes the growth of the sector, hence the need for a model that robustly predicts insurance uptake among potential clients. This study undertook a two...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nelson Kemboi Yego, Juma Kasozi, Joseph Nkurunziza
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	insurance uptake machine learning oversample random forest Bibliography. Library science. Information resources Z
Acceso en línea:	https://doaj.org/article/cbc9fbfd7c6e4b1389ac8b1d4145adbb
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cbc9fbfd7c6e4b1389ac8b1d4145adbb
record_format	dspace
spelling	oai:doaj.org-article:cbc9fbfd7c6e4b1389ac8b1d4145adbb2021-11-25T17:19:51ZA Comparative Analysis of Machine Learning Models for the Prediction of Insurance Uptake in Kenya10.3390/data61101162306-5729https://doaj.org/article/cbc9fbfd7c6e4b1389ac8b1d4145adbb2021-11-01T00:00:00Zhttps://www.mdpi.com/2306-5729/6/11/116https://doaj.org/toc/2306-5729The role of insurance in financial inclusion and economic growth, in general, is immense and is increasingly being recognized. However, low uptake impedes the growth of the sector, hence the need for a model that robustly predicts insurance uptake among potential clients. This study undertook a two phase comparison of machine learning classifiers. Phase I had eight machine learning models compared for their performance in predicting the insurance uptake using 2016 Kenya FinAccessHousehold Survey data. Taking Phase I as a base in Phase II, random forest and XGBoost were compared with four deep learning classifiers using 2019 Kenya FinAccess Household Survey data. The random forest model trained on oversampled data showed the highest F1-score, accuracy, and precision. The area under the receiver operating characteristic curve was furthermore highest for random forest; hence, it could be construed as the most robust model for predicting the insurance uptake. Finally, the most important features in predicting insurance uptake as extracted from the random forest model were income, bank usage, and ability and willingness to support others. Hence, there is a need for a design and distribution of low income based products, and bancassurance could be said to be a plausible channel for the distribution of insurance products.Nelson Kemboi YegoJuma KasoziJoseph NkurunzizaMDPI AGarticleinsurance uptakemachine learningoversamplerandom forestBibliography. Library science. Information resourcesZENData, Vol 6, Iss 116, p 116 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	insurance uptake machine learning oversample random forest Bibliography. Library science. Information resources Z
spellingShingle	insurance uptake machine learning oversample random forest Bibliography. Library science. Information resources Z Nelson Kemboi Yego Juma Kasozi Joseph Nkurunziza A Comparative Analysis of Machine Learning Models for the Prediction of Insurance Uptake in Kenya
description	The role of insurance in financial inclusion and economic growth, in general, is immense and is increasingly being recognized. However, low uptake impedes the growth of the sector, hence the need for a model that robustly predicts insurance uptake among potential clients. This study undertook a two phase comparison of machine learning classifiers. Phase I had eight machine learning models compared for their performance in predicting the insurance uptake using 2016 Kenya FinAccessHousehold Survey data. Taking Phase I as a base in Phase II, random forest and XGBoost were compared with four deep learning classifiers using 2019 Kenya FinAccess Household Survey data. The random forest model trained on oversampled data showed the highest F1-score, accuracy, and precision. The area under the receiver operating characteristic curve was furthermore highest for random forest; hence, it could be construed as the most robust model for predicting the insurance uptake. Finally, the most important features in predicting insurance uptake as extracted from the random forest model were income, bank usage, and ability and willingness to support others. Hence, there is a need for a design and distribution of low income based products, and bancassurance could be said to be a plausible channel for the distribution of insurance products.
format	article
author	Nelson Kemboi Yego Juma Kasozi Joseph Nkurunziza
author_facet	Nelson Kemboi Yego Juma Kasozi Joseph Nkurunziza
author_sort	Nelson Kemboi Yego
title	A Comparative Analysis of Machine Learning Models for the Prediction of Insurance Uptake in Kenya
title_short	A Comparative Analysis of Machine Learning Models for the Prediction of Insurance Uptake in Kenya
title_full	A Comparative Analysis of Machine Learning Models for the Prediction of Insurance Uptake in Kenya
title_fullStr	A Comparative Analysis of Machine Learning Models for the Prediction of Insurance Uptake in Kenya
title_full_unstemmed	A Comparative Analysis of Machine Learning Models for the Prediction of Insurance Uptake in Kenya
title_sort	comparative analysis of machine learning models for the prediction of insurance uptake in kenya
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/cbc9fbfd7c6e4b1389ac8b1d4145adbb
work_keys_str_mv	AT nelsonkemboiyego acomparativeanalysisofmachinelearningmodelsforthepredictionofinsuranceuptakeinkenya AT jumakasozi acomparativeanalysisofmachinelearningmodelsforthepredictionofinsuranceuptakeinkenya AT josephnkurunziza acomparativeanalysisofmachinelearningmodelsforthepredictionofinsuranceuptakeinkenya AT nelsonkemboiyego comparativeanalysisofmachinelearningmodelsforthepredictionofinsuranceuptakeinkenya AT jumakasozi comparativeanalysisofmachinelearningmodelsforthepredictionofinsuranceuptakeinkenya AT josephnkurunziza comparativeanalysisofmachinelearningmodelsforthepredictionofinsuranceuptakeinkenya
_version_	1718412495945728000

A Comparative Analysis of Machine Learning Models for the Prediction of Insurance Uptake in Kenya

Ejemplares similares