This project is ongoing. Descriptions, methods and results may be updated after further validation.
Research question
Are Pix security interventions associated with changes in the relative incidence and financial severity of fraud, in fund recovery and in system use?
Motivation
Pix made instant payments widespread in Brazil and, with them, scams in which the victim authorises the transfer. The Central Bank responded with a sequence of security rules; measuring their association with fraud and use helps calibrate regulation without slowing diffusion.
Data
- Monthly Pix and Special Return Mechanism (MED) statistics (Banco Central do Brasil open data)
- Chronology of security interventions, checked against official sources
Methodology
- Measurement audit of the public series
- Interrupted time series and ARIMAX models, conditional on series length and comparability
Limitations
- Manuscript at the pre-submission stage; results will be released after peer review.
- Comparable public series are short; analyses with fewer than 12 months before and after an intervention are treated as exploratory.
Implications
- Design and evaluation of security rules for instant payments.
Planned applied products (possible outreach, subject to registration)
- Teaching material on payments regulation and information systems