This is a project presented by Anita Sapre, Guddi Chauhan, Shraddha Ghosh, Swati Ranjan, and Vasudha Rao, PGP DSBA students, in the AICTE Sponsored Online International Conference on Data Science, Machine learning and its applications (ICDML-2020). A follow-up paper was published in the conference journal.
Family planning is one of the important aspects of the Safe Motherhood Initiative by the
World Health Organisation (WHO). The Safe Motherhood Initiative aims to reduce maternal death associated with unintended pregnancies. Unintended pregnancies carry serious consequences for the woman and their families, including the likelihood of unsafe abortion and delayed prenatal care, leading to poor maternal and child health outcomes. To improve the adoption of family planning among married women, a study of the prevalence of unmet need for family planning is imperative. WHO defines that women with unmet need are fecund and sexually active but are not using any method of contraception and report not wanting any more children or wanting to delay the next child. The concept of unmet need points to the gap between the women’s reproductive intentions and their contraceptive behaviour. A study was performed by the aforementioned students to understand how unmet needs for a woman can be predicted and, in turn, suggest appropriate family planning and public policy steps.
For this particular study, a ‘conditional’ unmet need was defined by considering women who are not using any contraceptive at the time of survey for the sample. The National Family Health Survey-4 (NFHS-4) data containing 155,880 currently married women are analyzed for this particular problem. The algorithms applied to predict the ‘conditional’ unmet need were Classification And Regression Tree (CART). At the Indian level, ‘conditional’ unmet need among currently married women is estimated at 43.3%. CART models at the state level provide rich insights into the differential impact of important predictors on the response variable. Accuracies of the CART models are in the range of 68% to 94%. The alternative measure of unmet need helps gain rich insights on the magnitude and directionality of the impact of several demographic, socioeconomic, and behavioural variables for the currently married women on the unmet need for family planning.
This study also showed how the ‘conditional’ unmet need amongst women varies with the fact if the firstborn is a son as compared to a daughter and how the ‘unmet’ need also varies with different regions of India as well comparing urban and rural families.
