United Nations Office on Drugs and Crime has reported that financial institutions spend USD 100 Billions on money laundering and financial compliance. Out of it USD 15-20 Billion on Enterprise software and analytics. Other than that, still companies are penalized to USD 35 Billion on Non-compliance. With Traditional rule based and Statistical approaches have proved inadequate, slow, laborious, and Expensive. Intelligent segmentation of people and behavior effects in the positive way for Anti-money laundering(AML) and Know Your Customer(KYC) Outcomes. Artificial Intelligence and machine Learning makes this possible with a little impact on existing system at both agile and scale. The key to attacking Anti-Money laundering threat lies in Intelligent segmentation across its life-cycle. This is beyond customer knowledge and diligence level. Here Artificial Intelligence and Machine learning plays an Important role. When the trusted data is layered from different sources, they can effectively streamline and increase the visibility on risk, based on behavior through the Know Your Customer/AML process.

In the boarding level of KYC Process AI and ML add Immense value. For Example, Image recognition features can verify the documents match by scanning different sources to evaluate the customer KYC risk Score. Customer data that is extracted from various sources can be transferred to onboarding system. A self-learning solution can create a dynamic questionnaire to evaluate customer identify. Then it adapts the response from the customer and map to intelligence gathered from different sources. Add-on based on mapping chatbots can be deployed to seek additional KYC Documents. At the operational level, combination of RPA(Robotic Process Automation), Natural language Processing and cognitive computing is potential positive factor. Using Sophisticated clustering techniques for example, Can group individuals by multiple parameters for highly reliable KYC risk assessment.

This information can be used to screen money laundering risk signals, match identities, and identify complex money laundering patterns and provide early alerts. AI and ML conduct real time analysis on transactions, their history and on multiple unstructured data source (Swift messages and anomalies in Invoice addresses). By constructing behavior archetypes and embedded predictive behavior analytic can enable the capture of risk signals with speed and accuracy. At the Reporting level, AI and ML adds continuous learning to constantly identify and map dynamic alert models and behaviors. For Example, Be it rogue employees, Insider trading, benchmark rigging or any other form of manipulation, they can analyze entire trading portfolios in real time to compare transaction behaviors and patterns. This will be used to identify trades intent in present and future possibility of committing fraud and market abuse. By using NLP and cognitive capabilities, banks and FI’s can automatically seek, analyze and implement regulatory changes and revisions. In addition, AI and ML enable banks to design Dashboards of Scenario analyzes for tax forecasting and reporting. Even they can bring greater transparency and accountability in data aggregation, analysis, thereby ensuring better compliance.