User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

Combining disparate data sources for improved poverty prediction and mapping

Primary tabs

download
  • Open access
  • PDF
  • 8.62 M
Pokhriyal, Neeti Jacques, Damien Christophe [UCL]

More than 330 million people are still living in extreme poverty in Africa. Timely, accurate, and spatially fine-grained baseline data are essential to determining policy in favor of reducing poverty. The potential of “Big Data” to estimate socioeconomic factors in Africa has been proven. However, most current studies are limited to using a single data source. We propose a computational framework to accurately predict the Global Multidimensional Poverty Index (MPI) at a finest spatial granularity and coverage of 552 communes in Senegal using environmental data (related to food security, economic activity, and accessibility to facilities) and call data records (capturing individualistic, spatial, and temporal aspects of people). Our framework is based on Gaussian Process regression, a Bayesian learning technique, providing uncertainty associated with predictions. We perform model selection using elastic net regularization to prevent overfitting. Our results empirically prove the superior accuracy when using disparate data (Pearson correlation of 0.91). Our approach is used to accurately predict important dimensions of poverty: health, education, and standard of living (Pearson correlation of 0.84–0.86). All predictions are validated using deprivations calculated from census. Our approach can be used to generate poverty maps frequently, and its diagnostic nature is, likely, to assist policy makers in designing better interventions for poverty eradication.

Document type Article de périodique (Journal article) – Article de recherche
Access type Accès libre
Publication date 2017
Language Anglais
Journal information "Proceedings of the National academy of sciences of the United States of America" - Vol. 114, no. 46, p. E9783-E9792 (26.09.2017)
Peer reviewed yes
Publisher National academy of sciences
issn 0027-8424
e-issn 1091-6490
Publication status Publié
Affiliation UCL - SST/ELI/ELIE - Environmental Sciences
Links
  1. Beegle Kathleen, Christiaensen Luc, Dabalen Andrew, Gaddis Isis, Poverty in a Rising Africa, ISBN:9781464807237, 10.1596/978-1-4648-0723-7
  2. Berdegué Julio A., Bebbington Anthony, Escobal Javier, Conceptualizing Spatial Diversity in Latin American Rural Development: Structures, Institutions, and Coalitions, 10.1016/j.worlddev.2014.10.015
  3. Okwi P. O., Ndeng'e G., Kristjanson P., Arunga M., Notenbaert A., Omolo A., Henninger N., Benson T., Kariuki P., Owuor J., Spatial determinants of poverty in rural Kenya, 10.1073/pnas.0611107104
  4. Eagle N., Pentland A., Lazer D., Inferring friendship network structure by using mobile phone data, 10.1073/pnas.0900282106
  5. World Bank (2016) World Development Report 2016: Digital Dividends (World Bank, Washington, DC).
  6. Oumar BA (2017) Poverty map in Senegal: A disparity in sharing wealth. Available at www.lesoleil.sn/2016-03-22-23-21-32/item/65075-carte-de-pauvrete-au-senegal-une-disparite-dans-le-partage-des-richesses.html. Accessed October 25, 2017.
  7. Rasmussen CE Williams CKI (2006) Gaussian Processes for Machine Learning (MIT Press, Cambridge, MA).
  8. Cressie Noel, The origins of kriging, 10.1007/bf00889887
  9. Zou Hui, Hastie Trevor, Regularization and variable selection via the elastic net, 10.1111/j.1467-9868.2005.00503.x
  10. Bahn Volker, McGill Brian J., Testing the predictive performance of distribution models, 10.1111/j.1600-0706.2012.00299.x
  11. Sundsøy P (2016) Can mobile usage predict illiteracy in a developing country? arXiv:1607.01337.
  12. Devarajan Shantayanan, Africa's Statistical Tragedy, 10.1111/roiw.12013
  13. Njuguna Christopher, McSharry Patrick, Constructing spatiotemporal poverty indices from big data, 10.1016/j.jbusres.2016.08.005
  14. Min Brian, Gaba Kwawu Mensan, Sarr Ousmane Fall, Agalassou Alassane, Detection of rural electrification in Africa using DMSP-OLS night lights imagery, 10.1080/01431161.2013.833358
  15. Eagle N., Macy M., Claxton R., Network Diversity and Economic Development, 10.1126/science.1186605
  16. Soto Victor, Frias-Martinez Vanessa, Virseda Jesus, Frias-Martinez Enrique, Prediction of Socioeconomic Levels Using Cell Phone Records, User Modeling, Adaption and Personalization (2011) ISBN:9783642223617 p.377-388, 10.1007/978-3-642-22362-4_35
  17. ITU World Telecommunication (2016) Key ICT indicators for developed and developing countries and the world. Available at www.itu.int/en/ITU-D/Statistics/Pages/default.aspx. Accessed October 21, 2017.
  18. Autorite de Régulation des Telecommunications et des Postes (2013) Observatoire de la telephonie mobile: Tableau de bord au 31 decembre 2013 ((Autorité de Régulation des Té lé communications et des Postes, Dakar, Senegal), Technical Report.
  19. Oxford Poverty and Human Development Initiative (2013) Country briefing: Senegal. Available at www.ophi.org.uk/wp-_content/uploads/Senegal-_2013.pdf?79d835. Accessed October 21, 2017.
  20. World Bank (2014) Overview. Available at www.worldbank.org/en/country/senegal/overview. Accessed October 21, 2017.
  21. Frías-Martínez V Soto V Virseda J Frías-Martínez E (2013) Can cell phone traces measure social development? Third Conference on the Analysis of Mobile Phone Datasets, NetMob 2013 (MIT Media Labs, Boston).
  22. Bogomolov Andrey, Lepri Bruno, Staiano Jacopo, Oliver Nuria, Pianesi Fabio, Pentland Alex, Once Upon a Crime : Towards Crime Prediction from Demographics and Mobile Data, 10.1145/2663204.2663254
  23. Jerven Morten, Comparability of GDP estimates in Sub-Saharan Africa: The effect of Revisions in Sources and Methods Since Structural Adjustment, 10.1111/roiw.12006
  24. de Montjoye Yves-Alexandre, Quoidbach Jordi, Robic Florent, Pentland Alex, Predicting Personality Using Novel Mobile Phone-Based Metrics, Social Computing, Behavioral-Cultural Modeling and Prediction (2013) ISBN:9783642372094 p.48-55, 10.1007/978-3-642-37210-0_6
  25. de Montjoye, J Machine Learn Res, 17, 1 (2016)
  26. Weidmann Nils B, Schutte Sebastian, Using night light emissions for the prediction of local wealth, 10.1177/0022343316630359
  27. Defourny P (2009) Accuracy assessment of a 300 m global land cover map: The globcover experience. Proceedings of the 33rd International Symposium on Remote Sensing of Environment (International Center for Remote Sensing of Environment, Tucson, AZ).
  28. Waldner François, Fritz Steffen, Di Gregorio Antonio, Defourny Pierre, Mapping Priorities to Focus Cropland Mapping Activities: Fitness Assessment of Existing Global, Regional and National Cropland Maps, 10.3390/rs70607959
  29. Samaké O., Smaling E.M.A., Kropff M.J., Stomph T.J., Kodio A., Effects of cultivation practices on spatial variation of soil fertility and millet yields in the Sahel of Mali, 10.1016/j.agee.2005.02.024
  30. Rockström J., de Rouw A., 10.1023/a:1004233303066
  31. Rasmussen, J Mach Learn Res, 11, 3011 (2010)
  32. Tibshirani, J R Stat Soc Ser B, 58, 267 (1996)
  33. Hoerl, Encyclopedia Stat Sci, 8, 129 (1988)
  34. Alkire S (2014) Mobilising the Household Data Required to Progress toward the Sdgs (University of Oxford, Oxford). Available at unsdsn.org/wp-content/uploads/2014/09/Mobilising-the-household-data-required-to-progress-toward-the-SDGs-WEB.pdf. Accessed October 24, 2017.
  35. Alkire Sabina, Foster James, Counting and multidimensional poverty measurement, 10.1016/j.jpubeco.2010.11.006
  36. Deville Pierre, Linard Catherine, Martin Samuel, Gilbert Marius, Stevens Forrest R., Gaughan Andrea E., Blondel Vincent D., Tatem Andrew J., Dynamic population mapping using mobile phone data, 10.1073/pnas.1408439111
  37. Alkire Sabina, Santos Maria Emma, Measuring Acute Poverty in the Developing World: Robustness and Scope of the Multidimensional Poverty Index, 10.1016/j.worlddev.2014.01.026
  38. von Mises R (1964) Chapter IX—Analysis of statistical data. Mathematical Theory of Probability and Statistics, ed von Mises R (Academic, Cambridge, MA), pp 431–493.
  39. Kim TH White H (2003) On More Robust Estimation of Skewness and Kurtosis: Simulation and Application to the S&P500 Index (Department of Economics, University of California, San Diego, La Jolla, CA).
  40. Hijmans Robert J., Cameron Susan E., Parra Juan L., Jones Peter G., Jarvis Andy, Very high resolution interpolated climate surfaces for global land areas, 10.1002/joc.1276
  41. Direction de l’Analyse, de la Prévision et des Statistiques Agricoles (2013) Rapport de Présentation des Résultats Définitifs de la Campagne Agricole 2012-2013 (Ministè re de l’Agriculture et de l’Équipement Rural, Dakar, Senegal), Technical Report.
  42. Jacques D (2015) Genesis of millet prices in Senegal: The role of production, markets and their failures. Fourth Conference on the Analysis of Mobile Phone Datasets, NetMob 2015 (MIT Media Labs, Boston).
  43. Leonardi U (2008) Senegal Land Cover Mapping (Food and Agriculture Organization, Rome), Technical Report.
  44. Dasgupta Susmita, Deichmann Uwe, Meisner Craig, Wheeler David, Where is the Poverty–Environment Nexus? Evidence from Cambodia, Lao PDR, and Vietnam, 10.1016/j.worlddev.2004.10.003
  45. Elbers Chris, Lanjouw Jean O., Lanjouw Peter, Micro-Level Estimation of Poverty and Inequality, 10.1111/1468-0262.00399
  46. Vista Brandon Manalo, Murayama Yuji, Spatial Determinants of Poverty Using GIS-Based Mapping, Spatial Analysis and Modeling in Geographical Transformation Process (2011) ISBN:9789400706705 p.275-296, 10.1007/978-94-007-0671-2_16
  47. Amarasinghe Upali, Samad Madar, Anputhas Markandu, Spatial clustering of rural poverty and food insecurity in Sri Lanka, 10.1016/j.foodpol.2005.09.006
  48. Minot N (2006) Poverty and inequality in Vietnam: Spatial patterns and geographic determinants (International Food Policy Research Institute, World Bank, Washington, DC). Available at siteresources.worldbank.org/INTPGI/Resources/342674-1092157888460/Minot.PovertyInequalityVietnam.pdf. Accessed October 24, 2017.
  49. Rogers D Emwanu T Robinson T (2006) Poverty mapping in Uganda: An analysisusing remotely sensed and other environmental data (Pro-Poor Livestock Policy Initiative, Food and Agriculture Organization, Rome), Working Paper No. 36.
  50. Benson Todd, Chamberlin Jordan, Rhinehart Ingrid, An investigation of the spatial determinants of the local prevalence of poverty in rural Malawi, 10.1016/j.foodpol.2005.09.004
  51. Kam Suan-Pheng, Hossain Mahabub, Bose Manik Lal, Villano Lorena S., Spatial patterns of rural poverty and their relationship with welfare-influencing factors in Bangladesh, 10.1016/j.foodpol.2005.10.001
  52. Watmough Gary R., Atkinson Peter M., Saikia Arupjyoti, Hutton Craig W., Understanding the Evidence Base for Poverty–Environment Relationships using Remotely Sensed Satellite Data: An Example from Assam, India, 10.1016/j.worlddev.2015.10.031
  53. Smith C Mashhadi A Capra L (2013) Ubiquitous sensing for mapping poverty in developing countries. Third Conference on the Analysis of Mobile Phone Datasets, NetMob 2013 (MIT Media Labs, Boston).
  54. Pokhriyal N Dong W (2015) Virtual network and poverty analysis in Senegal. Fourth Conference on the Analysis of Mobile Phone Datasets, NetMob 2015 (MIT Media Labs, Boston).
  55. Rao J.N.K., Molina Isabel, Small Area Estimation : Rao/Small Area Estimation, ISBN:9781118735855, 10.1002/9781118735855
  56. Blumenstock J., Cadamuro G., On R., Predicting poverty and wealth from mobile phone metadata, 10.1126/science.aac4420
  57. Jean N., Burke M., Xie M., Davis W. M., Lobell D. B., Ermon S., Combining satellite imagery and machine learning to predict poverty, 10.1126/science.aaf7894
  58. de Sherbinin Alex, VanWey Leah K., McSweeney Kendra, Aggarwal Rimjhim, Barbieri Alisson, Henry Sabine, Hunter Lori M., Twine Wayne, Walker Robert, Rural household demographics, livelihoods and the environment, 10.1016/j.gloenvcha.2007.05.005
Bibliographic reference Pokhriyal, Neeti ; Jacques, Damien Christophe. Combining disparate data sources for improved poverty prediction and mapping. In: Proceedings of the National academy of sciences of the United States of America, Vol. 114, no. 46, p. E9783-E9792 (26.09.2017)
Permanent URL http://hdl.handle.net/2078.1/188758