Poverty is one of the most urgent concerns regarding human development. It forces millions to live in negative conditions such as homelessness, food insecurity, inadequate nutrition, inadequate childcare, lack of access to healthcare or education, which all adversely impact our nations. Globally, poverty is a significant force of health and welfare challenges faced by humans today. While many institutions aim to alleviate poverty through donations and construction of infrastructure, they are often set back due to the difficulty of not knowing where exactly those that are affected live (Bill and Melinda Gates Foundation). With the inaccessibility of this information, developing countries are further set back from developing as they continue to struggle with the same unfreedoms. Researchers now using data science methods such as geospatial and satellite data can spatially target and produce accurate high-resolution maps of poverty indicators in developing countries.
In Amartya Sen’s “Development as Freedom,” Sen states that human development is the process of expanding human freedoms to allow people to lead the lives they have reason to live (Sen). Freedom is important because it leads to a higher quality of life. By targeting poverty-stricken areas and gathering data, we can use our freedoms to eradicate the unfreedoms of poverty in developing nations. Through this data, researchers can better understand poverty and its determinants in order to better design programs that reduce inequality and improve public service delivery among those who are extremely poor (Castelán). In this literature review, I will be assessing data science methods that are being used to indicate poverty-stricken regions and how the data can be used to eradicate poverty in Africa.
Poverty is the state at which an individual or community lacks financial resources or the essentials of a minimum standard of living. Millions of people around the world live in extreme poverty. They live lives without access to food, clean water, proper sanitation, or shelter. In 2015, 734 million people lived on $1.90 a day (United Nations). Governments, non-profits, and aid agencies have all made several efforts to alleviate poverty. However, they have all been unsuccessful due to a lack of access to developing countries and unreliable data. There is a lack of clear data to identify impoverished regions, leading to insufficient resource distribution (Kumar). To fix this issue, researchers are mapping poverty using satellite imagery along with census data as an alternative approach. Poverty mapping highlights inequalities within developing nations and provides an essential tool for the targeting of poverty alleviation policies (Bill and Melinda Gates Foundation).
I chose to assess poverty in Africa because it is the continent with the largest amount of people living in extreme poverty. Almost every second person living in the states of Sub-Saharan Africa lives under the poverty line. These people do not have access to basic human needs such as nutrition, clean water, shelter, and more. In Africa, extreme poverty leads to hunger, with more than a quarter of the hungry living on the African continent. 47% of the population lives on under $1.90 a day and they make up 70% of the global poor (SOS). Despite the overwhelming number of those living in poverty, the causes of poverty in Africa are no different than the causes of poverty all around the world. Some external factors include government corruption, poor infrastructure, exploitation of limited natural resources, lack of access to healthcare, food insecurity, limited access to clean water resources, and lack of shelter. Specifically, in Sub-Saharan Africa, poverty rates have risen due to the long-term effects of war, genocide, famine, and land availability. The burden of poverty is not only expected to be concentrated in Africa but also the number of people living in poverty is expected to continue rising. Africa’s rapid population growth is one long-term driving factor of this increase in poverty in the continent. Rapid population growth stretches national and family budgets thin with an increasing number of children to be fed and educated and an increasing number of workers to be provided with jobs. Lastly, I chose to research Africa because the availability of reliable and accurate information in the location of impoverished regions is generally lacking globally, but particularly in Africa (Horton). I was interested to learn how researchers could fill this gap in data and use data science techniques to locate poverty-stricken areas.
It is difficult to obtain reliable data from developing countries. Often, underdeveloped countries are highly data-deprived, so data science methods such as utilizing satellite imagery allow researchers to collect accurate and reliable data. Traditionally, methods used to target and analyze poverty rely on census data, which are often unavailable or out of date in most low- and middle-income countries (Steele). Alternative measures are needed to update estimates between censuses. Now, researchers use powerful machine learning technology to extract information about poverty through satellite imagery (Horton). The research article, “Mapping Poverty Using Mobile Phone and Satellite Data,” dives into how cell phone data is collected and paired with satellite information. RS data or remote sensing data collects physical properties of the earth, while CDR data, or call detail records, collects a detailed record of all telephonic calls produced by a telephone exchange. RS data and CDR data are a complementary pair when combined having the ability to capture human living conditions and behaviors. The poverty data in this study was represented using three geographically referenced datasets, including asset, consumption, and income-based measures of wellbeing in Bangladesh. The results of this study found that models with the combination of RS and CDR data provide an advantage over models with just the data source. The data showed that when RS data and CDR data were combined, they produced a higher R-squared value compared to RS-only or CDR-only data. However, the results also demonstrate that CDR-only and RS-only data models perform comparably in their ability to map poverty indicators. Poverty assessment and analysis have grown considerably with the utilization of CDR and RS data.
There are several data science methods I have found to be significant during my assessment of poverty in Africa. There are a various number of data science methods that go hand in hand when producing poverty maps. These methods include remote sensing (RS) data, call data record (CDR) data, geospatial data, and satellite data. These methods are used to analyze and assess poverty in various datasets. One method that stuck out to me was poverty mapping from cell phone and satellite data. The article, “Mobile Phones Can Create High-Resolution Poverty Map,” states that when combining mobile data and geospatial data from satellites, researchers were able to create poverty predictions with significant advantages when compared to those made from traditional sources, as census data isn’t regularly updated. Since information on mobile phones is ever changing and constantly updating, it can track changes on an ongoing basis. When paired with satellite data, it can provide a more dynamic view of poverty and its geographic spread. Mobile phones send information to receiving towers, giving an approximate location of the mobile user. It also contains information about data usage, number of texts sent and received, times of calls and their durations, etc. This anonymized data helps build a picture of poverty.
Another method I found interesting was geospatial methods such as the Rapid Consumption Methodology combined with geo-spatial data. In the article, “Estimating Poverty in a Fragile Context : The High Frequency Survey in South Sudan,” the author discusses poverty estimation in South Sudan using satellite data and the High-Frequency South Sudan Survey. Due to the lasting impacts of a civil war and the displacement of a third of the population, the last survey measuring poverty and consumption was conducted as far back as 2009. The growth and escalation of the civil war also posed a serious challenge to the planning of fieldwork. For this reason, the surveys capitalized on technology and methodological innovations to collect reliable data and provide accurate poverty estimates. To bridge this gap in data, the High-Frequency South Sudan Survey (HFS) implemented by the National Bureau of Statistics conducted several surveys across several states, measuring various characteristics such as consumption, poverty, welfare, currency devaluation, and inflation. By acquiring information from these regions of poverty, policies can be made to allow these developing countries to reach developmental freedom.
Lastly, another method I found interesting was using satellite imagery and geospatial methods such as sampling strategies using micro-listing and questionnaire design. In the article, “Estimation of Poverty in Somalia Using Innovative Methodologies,” the author discusses the estimation of poverty in Somalia. Like most low socio-economic countries, Somalia is a highly data-deprived country, leaving policymakers to operate in a statistical vacuum. The government had previously conducted the last population census in 1975. To overcome this gap in data, the World Bank implemented a Somali High Frequency Survey to better estimate poverty indicators. In this case, Somalia’s insecurity and lack of statistical infrastructure pose several challenges for implementing a survey and measuring poverty. Due to inaccessibility to certain areas because of the presence of terrorist groups, lack of a recent census, and the nature of a nomadic population, acquiring accurate information about the poverty indicators in Somalia proved to be challenging. This paper outlines how the SHFS estimated poverty indicators and overcame these challenges through methodological and technological adaptations. Using geospatial techniques and high-resolution imagery, they modeled the spatial population distribution, built a probability-based population sampling frame, and generated enumeration areas to overcome the lack of a recent population census. Poverty estimation in inaccessible areas relied on satellite imagery and other geospatial data. The geospatial data that was collected was used to create a security assessment access map, which gave researchers the ability to access the data from the inaccessible and unsafe regions in Somalia. All of these methods coupled together not only map out poverty, but also depict the quality of life, health of the community, economic well-being, and much more. The production of security assessment maps and poverty maps would allow Somalia and its citizens a better quality of life. With these maps, we can target the regions with high poverty and provide aid, benefits, and education to reduce the poverty rates.
With all our information gathered through these various data science methods, proper aid and funding can be administered to poverty-stricken regions efficiently and effectively, helping us understand the actual needs of those in poverty. Overall, data science gives an insight into the actual needs of the poor to formulate the proper poverty alleviation programs. With data and technology, researchers can understand the target group’s current and potential income source, providing a platform to identify the most valued components for social security. This would in turn help us in deciding what economic opportunities to promote or policies that could empower these groups and the level of aid that needs to be distributed. There are of course limitations, as machine learning technology is ever-changing and algorithms have elements of subjectivity. Nonetheless, data science methods allow us to dive deeper into human development issues and constantly monitor for improvement.
All the articles I have researched detailed the data science methods to alleviate poverty. From traditional census data to satellite imagery and geospatial techniques, there is one shared goal: to eradicate poverty. Overall, I believe that the digital economy is transforming how data is collected, processed, and used to make decisions. New methods, such as combining traditional household survey data with non-traditional data sources (satellite imagery and mobile phone data), are allowing researchers to map poverty at a higher scale and resolution and hopefully, helping countries continue to reduce poverty. However, there are still gaps in the literature that need to be addressed. I believe that all the articles detailed poverty mapping and prediction of poverty. However, they failed to address how the information was used. I am interested to know whether these methods and techniques of poverty assessment can be used in areas and regions where poverty is not as evident. The research question I pose after my analysis and readings is: Can the data created through predictive modeling and poverty mapping be utilized in regions where poverty is not as openly apparent?
Bill and Melinda Gates Foundation, World Bank, Grameen Foundation. “High Resolution Progress out of Poverty Mapping.” WorldPop, https://www.worldpop.org/portfolio/project?id=22. Accessed 30 Sept. 2021.
Castelán, Carlos Rodríguez, et al. “Making a Better Poverty Map.” World Bank Blogs, blogs.worldbank.org/opendata/making-better-poverty-map.
“Ending Poverty.” United Nations, United Nations, www.un.org/en/global-issues/ending-poverty.
Horton, Michelle. “Stanford Scientists Combine Satellite Data, Machine Learning to Map Poverty.” Stanford School of Earth, Energy & Environmental Sciences, pangea.stanford.edu/news/stanford-scientists-combine-satellite-data-machine-learning-map-poverty.
Kumar, Asmi. “How to Understand Global Poverty from Outer Space.” Medium, Towards Data Science, 6 July 2020, towardsdatascience.com/how-to-understand-global-poverty-from-outer-space-442e2a5c3666.
“On the Poorest Continent, the Plight of Children Is Dramatic.” SOS, www.sos-usa.org/about-us/where-we-work/africa/poverty-in-africa.
Pape, Utz; Parisotto, Luca. 2019. Estimating Poverty in a Fragile Context : The High Frequency Survey in South Sudan. Policy Research Working Paper;No. 8722. World Bank, Washington, DC. © World Bank. https://openknowledge.worldbank.org/handle/10986/31190 License: CC BY 3.0 IGO.
Pape, Utz; Wollburg, Philip. 2019. Estimation of Poverty in Somalia Using Innovative Methodologies. Policy Research Working Paper;No. 8735. World Bank, Washington, DC. © World Bank. https://openknowledge.worldbank.org/handle/10986/31267 License: CC BY 3.0 IGO.
Sen, Amartya Kumar. Development as Freedom. Oxford University Press, 2001.
Service, Indo-Asian News. “Mobile Phones Can Create High-Resolution Poverty Map.” India Today, 9 Feb. 2017, www.indiatoday.in/technology/news/story/mobile-phones-can-create-high-reolution-poverty-map-959791-2017-02-09.
Steele, Jessica E., et al. “Mapping Poverty Using Mobile Phone and Satellite Data.” Journal of The Royal Society Interface, vol. 14, no. 127, 2017, p. 20160690., doi:10.1098/rsif.2016.0690.