Predicting Inequality of Opportunity and Poverty in India Using Machine Learning

This introductory chapter discusses two major global challenges: poverty and inequality, with a special focus on unfair inequality linked to justice and equal access to opportunities. It draws on Roemer’s concept of inequality of opportunity (IOp), which refers to differences in people’s outcomes caused by circumstances beyond their control. Measuring poverty and IOp is difficult, especially in countries like India, due to limited and outdated data. To overcome this, the chapter highlights the use of innovative machine learning methods that combine traditional, non-traditional, and geospatial data. These tools can improve how we measure poverty and IOp with greater accuracy and timeliness. The chapter also sets the stage for the rest of the book, explaining why these issues matter. It outlines the key research questions, the unique contributions of the study, and the methods used. Finally, it offers an overview of what each chapter covers and how the book is structured.

This chapter explores the growing interest among scholars and policymakers in measuring inequality of opportunity (IOp) in income. It is well documented that focusing solely on inequality based on outcomes does not fully explain the rising income disparities within and across countries. It first traces the evolution of IOp concept and later presents empirical findings for India using the data from National Sample Survey (NSSO). The study employs both traditional and machine learning techniques to estimate income IOp. The results show that about 26–27% of income inequality in India can be attributed to factors beyond an individual's control. Parental education and occupation emerge as the most significant contributors to income IOp. Among regular workers, these parental backgrounds play a key role. For self-employed, gender is the primary driver of IOp, while for casual workers, geographical has the greatest impact. These findings highlight the importance of addressing unequal circumstances to promote a fairer and more inclusive society.

This chapter presents new ways to measure inequality of opportunity (IOp) in income for India, based on Roemer’s theory. It compares two methods: the ex-ante approach, which looks at outcomes before effort, and the ex-post approach, which considers outcomes after effort. Using machine learning tools such as conditional inference trees and transformation trees, the study finds that IOp explains 48–53% of income inequality in the ex-ante method, and about 34% in the ex-post method. Key factors driving IOp include parental education, region, rural-urban location, and parental occupation. The analysis shows that people from rural eastern and central India, marginalized social groups (like SCs and STs), and families with low education levels tend to earn the least. These patterns are consistent across both methods. The findings highlight the deep-rooted disadvantages some groups face. To reduce income IOp, the chapter calls for targeted regional policies and support for marginalized communities.

This chapter focuses on Sustainable Development Goal (SDG) 1, which aims to end poverty by 2030. Although significant progress has been made in poverty reduction, but the pace has slowed, especially after the COVID-19 pandemic. As of 2024, 8.9% of people global population live in extreme poverty, while 23.6% lives in poverty in low- and middle-income countries. South Asia, including India, continue to faces serious challenges especially in accurately measuring poverty. Traditional household surveys, while useful, are often costly, time-consuming, and outdated. To address this gap, this study explores the use of machine learning (ML) technique the combine geospatial and survey data to improve poverty prediction in India. It incorporates indicators such as nightlight intensity, land temperature, rainfall, vegetation, and points of interest. Among the ML models tested, the Random Forest algorithm produced the most accurate results. Nightlight intensity and point of interest density emerged as the most important predictors. These findings highlights the potential of ML tools to generate faster and more precise poverty estimates at local levels, offering valuable support for targeted policymaking.

This chapter studies inequality of opportunity in education in India and the key factors contributing these disparities. Using the ex-ante approach and machine learning algorithms, it analyses years of schooling as the outcome variable drawing from Periodic Labour Force Survey (PLFS) data. Input variables include gender, social group, parents’ education and occupation, and geographic region. The results reveal significant educational gap between rural and urban areas, as well as across gender and social groups. Gini coefficient of 0.22 indicate significant educational inequality, with about one-third of it stemming from circumstances beyond an individual’s control. Among all, parental education and geographical location emerge as the primary factors contributing to educational inequality. The study highlight the need for targeted policies to improve educational schools in underserved region, support marginalized communities, and promote gender equality.

This chapter studies inequality of opportunity (IOp) in access to health, with especial focus to maternal and child health services in India. It looks at five key services: immunization, institutional delivery, antenatal care, prenatal care, and care from trained professionals. A combined indicator called ‘adequate care’ measures overall access. Using the dissimilarity index and the Human Opportunity Index (HOI), the chapter assesses how fairly these services are distributed, based on NFHS-5 data. The results show high coverage rate for institutional deliveries and trained care, but low access to immunization and antenatal services. Overall, only 26% of women and children receive adequate care. Inequality is mostly due to differences in geography, income, and parents' education. In particular, the districts in Bihar, Jharkhand, Uttar Pradesh, and nearby areas show low access, while districts in Kerala, Tamil Nadu, Odisha, and Jammu & Kashmir perform much better. The study highlights the need for targeted health policies to bridge these regional and social gaps.

This chapter brings together the main findings from the earlier chapters, focusing on key challenges related to inequality of opportunity (IOp) and poverty in India. It discusses important policy directions to tackle these issues and suggests future areas for research. The chapter also reflects on the limitations of the study and the value it adds to existing knowledge.