Machine learning approach with multiple open-source data for mapping and prediction of poverty in Myanmar

Name: Htet, Nyan Lin

Name: Waree Kongprawechnon

Name: Isshiki, Tsuyoshi

Name: Suttipong Thajchayapongt

keyword: Open source data

LCSH: Poverty -- Myanmar -- Forecasting

LCSH: Machine learning

LCSH: Economic indicators -- Myanmar

LCSH: Cartography -- Remote sensing

Abstract: Poverty is rampant and a very crucial issue in developing countries. Therefore, in this paper, we explore the implementation of machine learning on the estimation of poverty by training input data from widely available and accessible open sources, including nighttime lights (NTL) and OpenStreetMap (OSM) data. We propose this approach as a straightforward, cost-effective, and alternative option to previous studies which have been conducted using deep learning. We applied linear regression and ridge regression algorithms as our baseline models while using random forest regression, gradient boosting regression, and XGBoost regression to achieve better performance. We found that our best model can explain approximately 74% of the variation in the wealth index from input features of Myanmar. We then created a poverty map at the provincial administrative level for Myanmar, which indicates that conventional machine learning models with open-source data can still be as efficient as deep learning for poverty estimation

King Mongkut's University of Technology North Bangkok. Central Library

Address: BANGKOK

Email: library@kmutnb.ac.th

Created: 2021

Modified: 2026-04-28

Issued: 2026-04-28

บทความ/Article

application/pdf

BibliograpyCitation : In Chiang Mai University. Faculty of Engineering. 2021 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON 2021) (pp.1041-1045). Chiang Mai : Chiang Mai University

eng

©copyrights King Mongkut's University of Technology North Bangkok

ใช้เวลา

0.025105 วินาที