Indian Statistics Ministry's Approach to Alternative Data Sources
The Indian Ministry of Statistics and Programme Implementation (MoSPI) is exploring the use of various alternative data sources to enhance the accuracy and comprehensiveness of official statistics, particularly for the new Consumer Price Index (CPI)-based retail inflation series. The initiative involves data from over-the-top (OTT) platforms, online portals for air and rail travel, and administrative records for fuel prices.
MoSPI's Data Integration Efforts
- MoSPI is in discussions with IRCTC and PPAC for direct data integration related to rail and fuel prices, respectively.
- Efforts are being made to use scanner data and web scraping to improve data collection.
- E-commerce websites are being considered as potential sources for price data.
Alternative Datasets for GDP Calculation
- Data from the Goods and Services Tax (GST), e-Vahan portal, and UPI transactions will be used by the National Statistics Office (NSO) for GDP calculations.
- The GSTN database is being utilized for surveys like the Annual Survey of Service Sector Enterprises.
Household Consumption Expenditure Surveys
Recent surveys have included questions on streaming services, air, and rail fares with specific weights assigned in the current CPI basket, such as:
- Airfare (economy class): 0.077%
- Railway fare: 0.185%
- Internet expenses: 0.08%
- Cable TV charges: 0.82%
- Mobile phone charges: 1.839%
Niti Aayog's Perspective on Alternative Data
Niti Aayog Vice Chairperson Suman Bery suggested that alternative data set exploration might be better suited for think-tanks rather than MoSPI, stressing that while beneficial, it should not overshadow other statistical tasks.
Advantages and Cautions
- Alternative data provides real-time insights into the economy's direction.
- Think-tanks like NCAER can play a significant role in data innovation.
- Chief Economic Adviser V Anantha Nageswaran emphasized the need to integrate alternative data judiciously with official statistics to ensure a balance between authenticity and innovation.
Future Plans for Data Series Base Revision
MoSPI is revising the base years for key datasets, with the GDP series set for release on February 27, 2026, using the financial year 2022-23 as the new base year. The IIP and CPI base years are also under revision, with new releases expected from 2026-27 onwards.