Research & Analysis
Reading Deck

Social Media Monitoring to Assess Consumer Risks in Digital Credit Apps: Guidance for Supervisors from an India Pilot

Following a study conducted in India, among other countries, and discussions with various stakeholders in the country on the effect of debt moratoria on low-income borrowers, CGAP became aware of emerging consumer risks related with digital credit in India. These risks mainly revolved around data misuse associated with irresponsible debt collection and data protection practices.  

To help monitor the digital credit market, assess consumer risks, listen to the collective voice of consumers, and identify potentially concerning providers, CGAP piloted a social media analysis tool in India based on Artificial Intelligence (AI). It used CGAP’s new typology of digital finance consumer risks and CGAP’s market monitoring toolkit (especially social media monitoring) as key frameworks.  

This reading deck contains supervisory guidance on the use of a branch of AI, Natural Language Processing (NLP), for social media monitoring, based on insights and lessons from the India pilot, and provides examples of social media analyses carried out as part of that pilot. Although guidance is presented in a general manner that goes beyond the India pilot, it still needs to be well contextualized before its application in a specific jurisdiction.  


  • The monitoring tool can track the nature of consumer risks in digital financial services, detect the consumers who are experiencing those risks, detect early warning signals in digital financial services, identify apps that merit their inclusion in a watch list, and run inexpensively and frequently once coding is established.  
  • However, it cannot detect the number and nature of complaints from those who cannot use social media, it cannot size the complaints in the market, and it does not enable the disaggregation of complaints by gender or income.
  • To implement this tool, supervisors need a strong foundation for the effective use of market monitoring tools, skills from a third-party vendor, and technical capacity to recruit and manage a specialized vendor.  

Related Resources


Some MCSs use supervisory technology (“suptech”) to convert large amounts of unstructured data into structured data. Suptech then combines the structured data with other data sources and formats, such as regulatory reporting, ultimately feeding all the data into supervisory risk analyses. Social media monitoring (or “social listening)” is one such unstructured data collection tool, which specifically focuses on consumer-generated data.

Last year, news reports emerged of aggressive debt collection amid India's digital credit boom. New research shows that early warning signs on social media preceded the reports, highlighting the value of social media for consumer protection.