Inflation Forecasting Based on Internet Search Queries

Diana A. Petrova – Researcher of the Russian Presidential Academy of National Economy and Public Administration (Moscow, Russia). E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

In recent times the accessibility of big data has risen with the increase of internet usage. The largest internet search engine Google provides statistics about the search activity. This study examines the usefulness of Google Trends intensity search queries data as a measure of economic expectations in predicting inflation during the period between January 2004 and July 2019. I use search queries related to financial markets, inflation expectations and macroeconomic conditions. The results show that the addition of Google search queries and machine learning methods improve inflation forecasting over benchmark model.

Key words: big data, inflation, Google Trends, forecasting, machine learning methods, seasonality, expectations, search queries.