Utilities of Artificial Intelligence in Poverty Prediction: A Review

Abstract

Artificial Intelligence (AI) is generating new horizons in one of the biggest challenges in the world’s society—poverty. Our goal is to investigate utilities of AI in poverty prediction via finding answers to the following research questions: (1) How many papers on utilities of AI in poverty prediction were published up until March, 2022? (2) Which approach to poverty was applied when AI was used for poverty prediction? (3) Which AI methods were applied for predicting poverty? (4) What data were used for poverty prediction via AI? (5) What are the advantages and disadvantages of the created AI models for poverty prediction? In order to answer these questions, we selected twenty-two papers using appropriate keywords and the exclusion criteria and analyzed their content. The selection process identified that, since 2016, publications on AI applications in poverty prediction began. Results of our research illustrate that, during this relatively short period, the application of AI in predicting poverty experienced a significant progress. Overall, fifty-seven AI methods were applied during the analyzed span, among which the most popular one was random forest. It was revealed that with the adoption of AI tools, the process of poverty prediction has become, from one side, quicker and more accurate and, from another side, more advanced due to the creation and possibility of using different datasets. The originality of this work is that this is the first sophisticated survey of AI applications in poverty prediction.

Effect of Zakat Potential Management on Achieving SDGs: Case of the Indonesian National Amil Zakat Agency

“…It purifies or increases or grows a person's wealth can be purified and this lead one's wealth to grow and be increased not only physically; but spiritually as paying zakat leads to an increase of barakah (blessing) of Allah (SW) in one's wealth (Muneeza & Nadwi, 2019;Shirazi, 2006;Islam et al, 2022). Zakat has an extra power not only to stabilize the condition when the economy is in disequilibrium and policies fail to recover and boost incomes immediately but also to enable the distributive allocation that works independently of business cycles and helps stabilize the extremes of business cycles (Efe, 2021;Usmanova, A., Aziz, A., Rakhmonov, D., & Osamy, W., 2022).…”

Predicting Multidimensional Poverty with Machine Learning Algorithms: An Open Data Source Approach Using Spatial Data

“…In addition, the cost of updating is high because surveys covering large territories are required. These are the main arguments for using new artificial intelligence technologies to estimate social indicators as a proxy of poverty, an area of research that has been growing in recent years Hall et al (2022); Usmanova et al (2022). Following these concerns, one seminal work was made by (Blumenstock et al 2015) using Call Detail Records (CDR) and the VIIRS-DNB satellite image data for predicting the wealth index in Rwanda from Demographic and Health Survey (DHS); the authors imple-mented deterministic finite automaton as feature extraction approach and linear methods with regularization approaches as the prediction algorithm.…”

“…To predict methods, there is a tendency to use multiple prediction algorithms in order to compare performances; one remarkable work uses several algorithms such as Random Forest, Gradient Boosting Machines, linear models with regularization, deep learning models, and new strategies such as the Stacked Learning Process (Pokhriyal et al 2020). However, studies that seek to advance the explanatory capacity of the models show that Random Forest is the best-performing algorithm Hu et al (2022); Liu et al (2021); Niu et al (2020); Puttanapong et al (2022); Usmanova et al (2022); in fact, the algorithm is considered one of the best options for poverty prediction Sohnesen and Stender (2017).…”

“…In general, estimating an MPI through spatial data has received limited attention, even when the first Sustainable Development Goal is to eradicate extreme poverty in all its forms everywhere, and even the world observed that the COVID-19 pandemic increased poverty rates Sachs et al (2021). However, it is essential to mention that the area of poverty prediction research using artificial intelligence algorithms is progressing rapidly Hall et al (2022); Usmanova et al (2022).…”

“…However, after pointing the way with satellite images, new studies started going beyond the use of night-light images to predict socioeconomic conditions and wealth index indicators as a poverty proxy (Ayush et al 2020;Engstrom et al 2017;Jean et al 2016;Lee and Braithwaite 2020;Steele et al 2017). AI tools are being applied to predict and select variables that can explain poverty Hall et al (2022); Usmanova et al (2022). However, given the importance of the need to make progress in eradicating poverty everywhere, the multi-source geospatial data on multidimensional poverty mapping are considered an open area not fully explored Hu et al (2022) as a source for both feature extraction and predictive variables.…”