Mapping poverty using mobile phone and satellite data

Abstract

Poverty is one of the most important determinants of adverse health outcomes globally, a major cause of societal instability and one of the largest causes of lost human potential. Traditional approaches to measuring and targeting poverty rely heavily on census data, which in most low- and middle-income countries (LMICs) are unavailable or out-of-date. Alternate measures are needed to complement and update estimates between censuses. This study demonstrates how public and private data sources that are commonly available for LMICs can be used to provide novel insight into the spatial distribution of poverty. We evaluate the relative value of modelling three traditional poverty measures using aggregate data from mobile operators and widely available geospatial data. Taken together, models combining these data sources provide the best predictive power (highest r2 = 0.78) and lowest error, but generally models employing mobile data only yield comparable results, offering the potential to measure poverty more frequently and at finer granularity. Stratifying models into urban and rural areas highlights the advantage of using mobile data in urban areas and different data in different contexts. The findings indicate the possibility to estimate and continually monitor poverty rates at high spatial resolution in countries with limited capacity to support traditional methods of data collection.

A Critical Review of High and Very High-Resolution Remote Sensing Approaches for Detecting and Mapping Slums: Trends, Challenges and Emerging Opportunities

“…Furthermore, that study also identified various locations where slum dwellers worked, which the authors suggested were influential in determining where slum dwellers relocate in and around Kibera. Recent work has also shown that when combined with remote sensing data, mobile phone data can be used to help discriminate slums from non slum areas [184]. The results of these studies and others highlight the increasing value of mobile device data as an unobtrusive and valuable source of information on slum populations.…”

To Impute or not to Impute? A Review of Alternative Poverty Estimation Methods in the Context of Unavailable Consumption Data

“…See also Pratesi (2016) for a recent collection of studies discussing various technical aspects of poverty mapping. Another study by Steele et al (2017) applies machine learning techniques and big data (i.e., cell phone and satellite data) to evaluate poverty mapping.…”

The Impact of Mobile Phone Uses in the Developing World

“…At the same time, however, it is imperative to resist the prominent temptation in ICT research of presenting trends or recipes of ICTs "seen as 'silver bullets' for development" (Walsham, 2014, p. 14). Indeed, several studies have proposed trends of mobile phones or ICTs along the lines of this paper, meaning not as positivistic absolute truths, but as qualitative, interpretive research or as tentative spaces of discussions (Aker & Blumenstock, 2015;Asongu, 2015aAsongu, , 2015bAsongu, Boateng, & Akamavic, 2016;Asongu & Nwachukwu, 2016a, 2016bChéneau-Loquay, 2010;Chipchase, 2009;Duncombe, 2016;Donner, 2008Donner, , 2015Donou-Adonsou, Lim, & Mathey, 2016;James, 2014James, , 2015James, , 2016Ojo, 2013;Porter, 2015;Reyes, 2016;Sam, 2017;Steele et al, 2017;Yan, 2015). It cannot be stressed enough that research is context-specific.…”

“…There are also promises in that mobile phone research is not tethered to a given journal or discipline. In effect, since coalescing into an articulate body of literature around the mid-2000s onward, the concept mobile phone has enjoyed a number of informative, synoptic accounts of produced literature (Aker & Blumenstock, 2015;Alderete, 2017;Asongu, 2015aAsongu, , 2015bAsongu, Boateng, & Akamavic, 2016;Asongu & Nwachukwu, 2016a, 2016bChéneau-Loquay, 2010;Donner, 2008Donner, , 2015Donner & Escobari, 2010;Donou-Adonsou, Lim, & Mathey, 2016;Duncombe, 2009aDuncombe, , 2009bDuncombe, , 2011Duncombe, , 2012Duncombe, , 2016Duncombe & Boateng, 2009;James, 2014James, , 2015James, , 2016James & Versteeg, 2007;Ojo, 2013;Porter, 2012Porter, , 2015Reyes, 2016;Sam, 2017;Steele et al, 2017;Yan, 2015). Meanwhile, it bears noting that with their booming combination with or transformation into specific services and applications (i.e., Internet, banking, ICTs, music, social media, etc.)…”

“…Indeed, attempts toward and concerns over mobile phone research emerged in the mid-2000s (Aminuzzaman, Baldersheim, & Jamil, 2003;Coyle, 2005Coyle, , 2007Donner, 2006;Gough, 2005;Singhal, Svenkerud, Malaviya, Rogers, & Krishna, 2005;Jensen, 2007;Waverman, Meschi, & Fuss, 2005;Williams, 2005). Since then exposés of mobile phone work ballooned into trends-traversed and development-sensitive subjects, with information systems for development alongside mobile phones or ICTs being one of the most prevailing subjects (Aker & Blumenstock, 2015;Alderete, 2017;Asongu, 2015aAsongu, , 2015bAsongu, Boateng, & Akamavic, 2016;Asongu & Nwachukwu, 2016a, 2016bChéneau-Loquay, 2010;Donner, 2008Donner, , 2015Donou-Adonsou, Lim, & Mathey, 2016;Duncombe, 2016;James, 2014James, , 2015James, , 2016James & Versteeg, 2007;Ojo, 2013;Porter, 2015;Reyes, 2016;Sam, 2017;Steele et al, 2017;Yan, 2015). One deep-seated shortcoming of mobile phone research invariably pointed out across most literature is that of anecdotal, melodramatic, loose, spurious, insufficient, or unsupported claims about development.…”