An AML SupTech Solution for the Mexican National Banking and Securities Commission (CNBV) - R2A Project Retrospective and Lessons Learned

19 Pages Posted: 2 Jun 2020

See all articles by Simone di Castri

Simone di Castri

Cambridge SupTech Lab - University of Cambridge; University of Cambridge - Cambridge Centre for Alternative Finance

Matt Grasser

Cambridge SupTech Lab - University of Cambridge; BFA; University of Cambridge - Cambridge Centre for Alternative Finance

Arend Kulenkampff

Independent

Date Written: October 26, 2018

Abstract

Supervisory Technology (SupTech) is poised to effect a paradigm shift in the fight against financial crime. SupTech-based data architectures that combine advanced data transmission, storage, and analytical technologies have the potential to dramatically enhance the accuracy, efficiency, and predictive power of traditional AML approaches, or supplant them altogether. In addition to automating many of the manual tasks in traditional methods, such as painstakingly reconciling FIs’ suspicious activity reports, supervisors can now leverage Big Data applications to scrutinize the raw transactional and customer data themselves drawing on historical and real time data. Cutting down on preparation and travel time for data collection frees up time and resources for deeper off-site analysis and more frequent on-site inspections. Dynamic and interactive dashboards helps supervisors visualize data in novel ways and draw insights that might have been previously hidden, which also helps to make investigations more targeted. Similarly, innovative machine learning models allows regulators and supervisors to identify new patterns of suspicious activities not detectable by manual analysis. This case studies describes the CNBV’s prototype developed under the auspices of R2A, which demonstrated large efficiency gains that could be reaped from a full-scale roll-out of this solution, particularly in time saved from routine manual work. Data collection and processing that required weeks and days of manual work under the traditional approach can now be completed in minutes and seconds. New analytical models also delivered concrete results that supervisors can already use to improve anomaly detection. With more data mining and machine learning, these models are likely to uncover more illicit activity or even predict money laundering before it happens.

Keywords: suptech, regtech, aml, aml/cft, anti-money laundering, central bank, financial intelligence unit, financial crime, mexico, cnbv, fatf, financing of terrorism, artificial intelligence, machine learning

Suggested Citation

di Castri, Simone and Grasser, Matt and Kulenkampff, Arend, An AML SupTech Solution for the Mexican National Banking and Securities Commission (CNBV) - R2A Project Retrospective and Lessons Learned (October 26, 2018). Available at SSRN: https://ssrn.com/abstract=3592564 or http://dx.doi.org/10.2139/ssrn.3592564

Simone Di Castri (Contact Author)

Cambridge SupTech Lab - University of Cambridge ( email )

NY
United Kingdom

University of Cambridge - Cambridge Centre for Alternative Finance ( email )

Matt Grasser

Cambridge SupTech Lab - University of Cambridge ( email )

NYC
United Kingdom

HOME PAGE: http://cambridgesuptechlab.org

BFA ( email )

259 Elm Street, Suite 200
Somerville, MA 02144
United States

University of Cambridge - Cambridge Centre for Alternative Finance ( email )

Arend Kulenkampff

Independent ( email )

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
494
Abstract Views
1,599
Rank
105,549
PlumX Metrics