In part I of this series, we learned about the background of KYC/ AML sector and understood the similarities and differences between AI, machine learning (ML) and robotic process automation (RPA). In this article we will explore the applications of these technologies in the KYC/AML context.

 

Benefits of AI for the KYC/AML Sector

In the financial industry and especially in KYC/AML, fraud and financial sanctions areas, AI is increasingly being used to improve the quality of data. This provides detailed information for decision-making processes that determine whether a client relationship should continue based on risk level. Sophisticated ML algorithms can monitor client activity, verify viable and fraudulent transactions and analyze client networks at lightning speed. This includes examining their personal transactions, especially designated nationals and politically-exposed persons in their environment.

AI can automatically update client risk profiles and match against various risk classifications, to ensure continued compliance throughout the client life cycle.

AI’s ability to read vast amounts of structured and unstructured data enables real-time analysis of sudden transfers between bank accounts, flagging previously stagnant accounts that register suspicious transactions over a short period of time. Many financial institutions have gained awareness of these unusual behaviors only after carrying out a detailed study of a specific group of clients over an extended period of time, burning through resources.

AI on the other hand, can monitor this constantly. ML’s ability to learn from the information that passes through them, allows the prediction and mapping of behavior patterns, giving institutions the chance to be preventive rather than reactive. A combination of AI and ML can enable financial institutions to reduce their exposure to the risk of penalties and fines from national and international regulators.

The following figure shows the four KYC phases and process steps with practical use examples of AI, ML and RPA:

AI application examples in the KYC/AML process

AI application examples in the KYC/AML process

 

 

Machine Learning: Reducing False Positives and Compliance Costs

AI can have a huge impact on reducing the number of false positives detected by traditional transaction-based parameters and thus result in lower compliance costs.

Classical transaction monitoring tools perform based on static rules that were set up beforehand. For example, if a recorded transaction is higher compared to historic accounts for a client, the monitoring tool will generate an alert. This usually ends up as a false positive. For instance, a client that might have started a new job after university will set off an alert. Around 90-95%2 of the alerts are false positives.

AI tools on the market are able to continuously learn from external data sources like OFAC/PEP lists and transactions. AI tools analyze client account behavior and understand the data that goes through the machine. Dynamic-rule based AI tools adapt using ML algorithms. The following figure shows the annual cost of transaction monitoring of a bank which has two teams to manage all the alerts generated. The example reflects the high operational costs.

Example of transaction monitoring costs

The use of AI technology improves the accuracy of the alert generation reducing the number of false positives leading to savings.

 

RPA: Reducing Repetitive Tasks to Optimize Resources

A straightforward example of how RPA could be applied in the KYC/AML area is the automated data downloading from the German Trade Register (commercial register) to perform KYC periodic review. Most of this work is currently manual: the analyst downloads the information by hand, compares it with the previous register and enters the changes in the respective systems.

Thanks to RPA, a bot could assist analysts by undertaking repetitive tasks faster and with minimal errors, leaving them with more time for important activities.

This process could be scheduled to recur on specific dates and times, triggered by specific events like an incoming e-mail or started by a person.

Summary of benefits of AI in the KYC/AML Sector.

Summary of benefits of AI in the KYC/AML Sector.

The automation journey is a multi-faceted one and the financial services industry can greatly benefit from significantly reducing processing times and minimizing human errors, thus increasing productivity and adding value to their business.

The time is now ripe for financial institutions to take note and incorporate these advanced technologies that have incalculable potential to transform the sector and enhance customer experience.

Gerardo Salonia

Gerardo Salonia

Principal, Infosys Consulting

Gerardo Salonia is a principal within our financial services practice in Germany with a focus on compliance, AML and KYC areas. He has extensive consulting experience within the e-commerce and financial services domain. Gerardo has enabled several European companies and financial institutions to overcome the challenges posed by disruptive technologies and transform into digital-oriented organizations. Gerardo holds an MBA in business administration from the University of Mannheim. He is a certified AML officer and has a risk management certification from the Goethe Business School – Frankfurt University.

Ana Carolina Cruz Aguilar

Ana Carolina Cruz Aguilar

Senior Consultant, Infosys Consulting

Ana Carolina Cruz Aguilar is senior consultant within our Artificial Intelligence & Automation practice at Infosys Consulting, Germany. Her focus lies in helping organizations leverage the full potential of the latest digital technologies. She also has extensive banking experience, mainly in the credit risk controlling area. Carolina holds an M.Sc. in Mathematical Sciences from the National University of Mexico and is certified Data Scientist from The Data Incubator Reply program.
Mile Dragosavac

Mile Dragosavac

Senior Consultant, Infosys Consulting

Mile Dragosavac is senior consultant within our Artificial Intelligence & Automation practice at Infosys Consulting, Germany. His focus lies in business intelligence topics leveraging data driven decisions using machine learning. He also has extensive banking experience, mainly in the credit risk controlling area and multi asset management. Mile holds an MBA in economics from the University of Mannheim and is certified applied Data Scientist from University of Michigan.

Pin It on Pinterest

Share This