Page 117 - Invited Paper Session (IPS) - Volume 2

IPS 188 G. P. Samanta

Does Google search index help track and predict
inflation rate? An exploratory analysis for India
G. P. Samanta
1

Abstract
The forward looking outlook or market expectations on inflation constitute
valuable input to monetary policy, particularly in the ‘inflation targeting'
regime. However, prediction or quantification of market expectations is a
challenging task. The time lag in the publication of official statistics further
aggravates the complexity of the issue. One way of dealing with non-
availability of relevant data in realtime basis involves assessing the current or
nowcasting the inflation based on a suitable model using past or present data
on related variables. The forecast may be generated by extrapolating the
model. Any error in the assessment of the current inflationary pressure thus
may lead to erroneous forecasts if the latter is conditional upon the former.
Market expectations may also be quantified by conducting suitable surveys.
However, surveys are associated with substantial cost and resource
implications, in addition to facing certain conceptual and operational
challenges in terms of representativeness of the sample, estimation
techniques, and so on. As a potential alternative to address this issue, recent
literature is examining if the information content of the vast Google trend data
generated through the volume of searches people make on the keyword
‘inflation' or a suitable combination of keywords. The empirical literature on
the issue is mostly exploratory in nature and has reported a few promising
results. Inspired by this line of works, we have examined if the search volume
on the keywords ‘inflation’ or ‘price’in the Google search engine is useful to
track and predict inflation rate in India. Empirical results are very encouraging.
Future research may focus on fine-tuning of the present work further and to
check the robustness of the results over time and across countries.

Keywords
Inflation Expectations; Surveys; Internet Search; Google Trend; Google search
Index

1 G.P.Samanta is an Adviser in the Department of Statistics and Information Management
(DSIM), Reserve Bank of India (RBI). The results presented in the paper and the views expressed
are purely personal and may not represent those of the institute/organization he belongs to.
Comments and suggestions are welcomed. The authour can be reached through email at
gpsamanta@rbi.org.in.
104 | I S I W S C 2 0 1 9