Reserve Bank of India study: Night-time satellite lights and Google Trends data reduce state growth estimation errors by up to 62%

Key facts

• A Reserve Bank of India (RBI) study, published in the RBI October Bulletin, found that combining satellite-based night-time lights with Google search data can reduce state-level economic growth estimation errors by up to 62%.
• The study, titled 'Nowcasting State-Level Economic Activity in India with Night-Time Light and Google Trends', developed a quarterly framework to track economic activity in Gujarat, Maharashtra and Karnataka.
• Gross State Value Added (GSVA) figures are released annually with a lag of 12-18 months, limiting real-time assessment of state economies.
• The model combined satellite night-time illumination data with Google Trends search indices across 25 categories, including jobs and education, finance, shopping, real estate and automobiles.
• Adding both night-time lights and Google search data reduced the root mean squared error (RMSE) by about 38% for Maharashtra, 54% for Karnataka and 62% for Gujarat.
• The correlation between year-on-year night-time lights growth and GSVA growth was highest in Maharashtra at 0.90, followed by Karnataka at 0.79 and Gujarat at 0.66.
• Night-time light data provided predictive information about subsequent GSVA growth, while Google Trends data contributed mainly through contemporaneous signals.
• The framework was tested only in three industrial states and is intended to complement, not replace, official economic statistics.