The Granular Solution To Effective Policy Targeting

With the right data quality, policy efficiency is no more a pipe dream but rather within the grasps of big data analytics


Policy making and targeting in India has always been contentious and has largely revolved around data analysis at the national or state-levels. The finest data analysis that is done is through studies such as Census, which are typically held once in a decade with questionable data quality and the smallest unit of estimation being the household. Due to these issues, the baseline depiction is unreliable. Efficient policy targeting at micro regions and specific demographics cannot be undertaken based on this, setting a self-contradictory process of resource allocation.

However, recent research shows the power of big data that can be harnessed through spatially granular data units of as small as individual level data to accurately predict the Global Multi Dimensional Poverty Index. Pokhriyal and Jacques (2017) have been able to measure poverty and map the same at the commune level in Senegal, by leveraging unprecedented volumes of call data records combined with physical/natural environment variables such as elevation, urban areas, roads, etc. Specific features of call data records, such as the number of active days (for call and text) characterized that individuals in wealthier communes have monetary resources to recharge their phone and make/receive calls and are negative predictors of poverty, while the ratio of calls vs. text shows the preference for calls, and emerged as an important factor to predict education-based deprivations. Mobility data patterns of individuals could also be captured using spatial features such as number of frequent antennas, entropy of antennas, and total number of antennas used by an individual, and indicated a negative relationship to poverty.

While such studies can be replicated for India and do imply massive insights for socio-economic and policy analysis and application, currently such innovative methods are underutilised. Individual level data is largely unavailable and has not been widened in use application much. Increasingly, nightlights data has gained popularity to proxy economic activity and subsequently gain insights at state and neighbourhood levels. Besides these obviously rich data sources, there exist a number of ways that big data can drive efficiency for the government, firms and individuals. The array of tools and methods available at hand make for a unique proposition to combine geographical information systems and satellite data to accurately represent spatially heterogeneity of factors at various micro regions, driving home insights that are far more useful than just analysis of macro data broken down state-wise. Location and predictive analytics are being widely used along with the upcoming streams of social listening. With a profound data stack, these methods possess unlimited solutions to any geo-demographic problems that exist.

The technology already exists and is being used in India to deliver tangible results. An advanced data analytics platform can analyze multiple data streams from both rural and urban GDPs and map the smallest economies. The right statistical tools can help conduct land use analysis by laying data based on geography, land, built up structures. This analysis coupled with relevant demographic data can provide a rich context for deriving insights. Algorithms that correlate factors such as age, income, concentration of competition and relative development of an area and the probability of the success of geo-profiled areas, can also be applied to this data layering process can also be used to create maps of banked and unbanked areas

With the right data quality, policy efficiency is no more a pipe dream but rather within the grasps of big data analytics. These innovative processes, once identified, have unlimited potential to improve the functioning of the Indian economy. The Senegal study could be then replicated for India not just for poverty analysis but also a Gini index micro region analysis and with further research, could also posit a solution for the public distribution system that has been blamed for the maximum misuse of resources and misallocation.

Disclaimer: The views expressed in the article above are those of the authors’ and do not necessarily represent or reflect the views of this publishing house. Unless otherwise noted, the author is writing in his/her personal capacity. They are not intended and should not be thought to represent official ideas, attitudes, or policies of any agency or institution.


Covered  by :-