All you Need is Text. Using Text Mining to Identify Tax Reform Episodes
This session illustrates how text mining can help extract and
classify granular information on tax policy actions from tens of
thousands of documents, discussing economic developments in 23
advanced and emerging market economies over the last four decades.
Manasa Patnam (SPR) Panelist
Mobile Money and Financial Inclusion in India
This talk will explore the impact of mobile money on financial
access and economic activity in India. Using granular and
high-frequency transaction data from PayTM, one of the largest mobile
money firm in India, and combining this with other spatially
disaggregated data (such as satellite night-time lights and firm
censuses), we document what factors drive the adoption of mobile
money, and whether mobile payments help increase the resilience to shocks.
Andrew Tiffin (MCD) Panelist
Exploring Causal Relationships with Machine Learning (ML)
The talk will introduce some recent work in the area of “causal” ML
using a concrete policy-relevant example—assessing the impact of a
hypothetical banking crisis on a country’s growth. Showcasing some
specific country examples, we aim to highlight how machine learning
can provide an invaluable complement to the skill set of economists
within the Fund and beyond.