© Copyright 2019 marcus evans. All rights reserved.

For all enquiries regarding speaking, sponsoring and attending this conference contact:

Yiota Andreou
Email: Yiotaa@marcusevanscy.com 
Telephone: +357 22849 404
Fax: +357 22 849 394

2nd Edition

Automation in AML Compliance and Modeling

13-15 May 2019 -Chicago, United States of America

Could you please elaborate on the importance of AML risk modeling?

AML risk modelling will become increasingly important to match the increasing sophistication in money laundering schemes.

Advanced methods can identify more complex criminal activity as well as adapt to and identify changes in behaviour quickly.

Additionally, as many financial institutions move to advanced modelling methods for AML, those institutions not adopting advanced methods could be at risk. 

How are AML models different from other financial models? 

AML models have many regulatory requirements in the factors and scenarios that have to be considered in the transaction monitoring, leading to a development process that is a hybrid of qualitative and quantitative factor selection and has some inefficiency due to a high false positive rate across the industry.

Also, AML models do not always have a risk appetite that sets an acceptable capture of potential AML events, making the trade-off between precision and efficiency challenging. 

How can AML modeling and compliance teams work together to more effectively identify suspicious activity?

The AML compliance team should provide feedback to the model developers on emerging risks that they are seeing but are not yet evident in the data for inclusion in transaction monitoring.

Then the AML modelling team should communicate factors identified through modelling on historical transactions to AML compliance so that investigators can review utilize these factors in investigations. 

How are emerging technologies like machine learning being used in AML modeling?

Machine learning is most commonly being used to risk score alerts, so that low risk alerts can be closed with minimal investigation (or auto-closed), and high risk alerts receive the greatest attention of investigators.

Machine learning could also be used to make transaction monitoring more efficient, but the scenarios required by regulation will still result in an inherent inefficiency, leading most financial institutions to risk score alerts for more efficient use of investigator resources. 

What would you like to achieve by attending the 2nd Edition Automation in AML Compliance and Modeling Conference?
I would like to confer with colleagues on best practices in AML modelling and uses of machine learning methods on the following:

• What works and what doesn’t in increasing efficiency of alert review through the use of advanced modelling methods. 
• How to work collaboratively with AML compliance experts and investigators. 
• What data requirements are being set in the industry to support advances in AML modelling.
  

An interview with:

Shannon Kelly
Senior Vice President,
Director Model Risk Management at Zions Bancorporation

By attending this conference, you will learn how to work with your local regulator to implement automation technologies in your AML program and gather sufficient data to comply with Customer Due Diligence (CDD) requirements. You will also develop machine learning techniques to build a stronger AML model and AI solutions to reduce false alerts. Finally, practical demonstrations on how to avoid “black boxes” in an automated system will enable you to fill out a comprehensive Suspicious Activity Report (SAR).

To view the Conference Agenda, click HERE! 

Follow us on Social Media!

How are AML models different from other financial models

We would be delighted to provide you with more information on the conference agenda.  Please fill in your details below and we will be in touch.

Shannon is the Director of Model Risk Management at Zions Bancorp. She has over eighteen years of financial service industry experience, including the US Head of Model Risk Management at TD Bank, Head of Enterprise Risk Management Audit at Bank of the West, and Director of Economic Capital at HSBC Bank US.  She also worked for the Federal Reserve Bank of Philadelphia specializing in retail credit risk models and Basel II examinations and regulatory guidance.  Shannon has a Master’s degree in mathematics and statistics from Cornell University and a Bachelor’s degree in mathematics from the University of Washington in Seattle.

To view the Conference Agenda, click HERE!