Enhancing poverty classification in developing countries through machine learning: a case study of household consumption prediction in Rwanda

To address the challenges associated with measuring and classifying household consumption (poverty) in developing countries, such as cost, time gaps, and inaccurate socio-economic data, this study suggests leveraging machine learning (ML) algorithms. We assessed the performance of various ML algorit...

Full description

Saved in:
Bibliographic Details
Main Authors: Fabrice Nkurunziza, Richard Kabanda, Patrick McSharry
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Cogent Economics & Finance
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/23322039.2024.2444374
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850052619895046144
author Fabrice Nkurunziza
Richard Kabanda
Patrick McSharry
author_facet Fabrice Nkurunziza
Richard Kabanda
Patrick McSharry
author_sort Fabrice Nkurunziza
collection DOAJ
description To address the challenges associated with measuring and classifying household consumption (poverty) in developing countries, such as cost, time gaps, and inaccurate socio-economic data, this study suggests leveraging machine learning (ML) algorithms. We assessed the performance of various ML algorithms using data from 14,580 sample households from the Integrated Household Living Condition Survey (EICV5), considering 87 features. Among the 12 classifiers evaluated, multiple kernel support vector machines, eXtreme gradient boosting, and multinomial logit demonstrated the highest predictive accuracy, ranging between 86.6% and 88.5%. Notably, household food expenditure, the total number of children (<14 years) in the household, and household own food expenditures emerged as the most predictive features for consumption classification. Interestingly, including shock-coping strategies did not significantly improve prediction accuracy. The multiple kernel support vector machine consistently outperformed eXtreme gradient boosting and multinomial logit. These findings suggest that survey questions used to assess poverty in Rwanda could be streamlined, prioritizing important features, particularly those related to household food characteristics. This approach has the potential to address challenges associated with measuring and classifying household consumption in developing countries more effectively.
format Article
id doaj-art-465844e09f4d4a97bfedb4fa28a2da73
institution DOAJ
issn 2332-2039
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Cogent Economics & Finance
spelling doaj-art-465844e09f4d4a97bfedb4fa28a2da732025-08-20T02:52:46ZengTaylor & Francis GroupCogent Economics & Finance2332-20392025-12-0113110.1080/23322039.2024.2444374Enhancing poverty classification in developing countries through machine learning: a case study of household consumption prediction in RwandaFabrice Nkurunziza0Richard Kabanda1Patrick McSharry2The African Centre of Excellence in Data Science, University of Rwanda (UR), Kigali, RwandaThe African Centre of Excellence in Data Science, University of Rwanda (UR), Kigali, RwandaDepartment of Electrical and Computer Engineering, Carnegie Mellon University, Kigali, RwandaTo address the challenges associated with measuring and classifying household consumption (poverty) in developing countries, such as cost, time gaps, and inaccurate socio-economic data, this study suggests leveraging machine learning (ML) algorithms. We assessed the performance of various ML algorithms using data from 14,580 sample households from the Integrated Household Living Condition Survey (EICV5), considering 87 features. Among the 12 classifiers evaluated, multiple kernel support vector machines, eXtreme gradient boosting, and multinomial logit demonstrated the highest predictive accuracy, ranging between 86.6% and 88.5%. Notably, household food expenditure, the total number of children (<14 years) in the household, and household own food expenditures emerged as the most predictive features for consumption classification. Interestingly, including shock-coping strategies did not significantly improve prediction accuracy. The multiple kernel support vector machine consistently outperformed eXtreme gradient boosting and multinomial logit. These findings suggest that survey questions used to assess poverty in Rwanda could be streamlined, prioritizing important features, particularly those related to household food characteristics. This approach has the potential to address challenges associated with measuring and classifying household consumption in developing countries more effectively.https://www.tandfonline.com/doi/10.1080/23322039.2024.2444374Household consumptionSupport Vector machineeXtreme Gradient Boostingmultinomial logitRwandaC52
spellingShingle Fabrice Nkurunziza
Richard Kabanda
Patrick McSharry
Enhancing poverty classification in developing countries through machine learning: a case study of household consumption prediction in Rwanda
Cogent Economics & Finance
Household consumption
Support Vector machine
eXtreme Gradient Boosting
multinomial logit
Rwanda
C52
title Enhancing poverty classification in developing countries through machine learning: a case study of household consumption prediction in Rwanda
title_full Enhancing poverty classification in developing countries through machine learning: a case study of household consumption prediction in Rwanda
title_fullStr Enhancing poverty classification in developing countries through machine learning: a case study of household consumption prediction in Rwanda
title_full_unstemmed Enhancing poverty classification in developing countries through machine learning: a case study of household consumption prediction in Rwanda
title_short Enhancing poverty classification in developing countries through machine learning: a case study of household consumption prediction in Rwanda
title_sort enhancing poverty classification in developing countries through machine learning a case study of household consumption prediction in rwanda
topic Household consumption
Support Vector machine
eXtreme Gradient Boosting
multinomial logit
Rwanda
C52
url https://www.tandfonline.com/doi/10.1080/23322039.2024.2444374
work_keys_str_mv AT fabricenkurunziza enhancingpovertyclassificationindevelopingcountriesthroughmachinelearningacasestudyofhouseholdconsumptionpredictioninrwanda
AT richardkabanda enhancingpovertyclassificationindevelopingcountriesthroughmachinelearningacasestudyofhouseholdconsumptionpredictioninrwanda
AT patrickmcsharry enhancingpovertyclassificationindevelopingcountriesthroughmachinelearningacasestudyofhouseholdconsumptionpredictioninrwanda