Client Introduction

Our Client is a leading American Fortune 500 finance company.

The Challenge

Their use-case requirements were:

• Reduce credit risk exposure to entities and stakeholders that had fraudulent linkages and serious litigations.
• Automate existing client processes that were highly manual and involved going through hundreds of publicly available data sets.
• Reduce errors brought on as a result of such manual processes.

Solution Overview

• We implemented the MLens Platform to adopt ML algorithms to identify features, develop models, and calculate the impact of key datasets included Corporation, Entity, Holding Information, Financial Transaction Details and publicly available datasets.
• Built a crawling and indexing solution to intelligently identify links that contain relevant information, and extract the content.
• Performed Named Entity Recognition, Relationship Mining and Fuzzy Matching to link enterprise data with public datasets, and highlight linkages to fraud/ litigation.
• Provided a self-service dashboard to visualize clustered topics, free-form search and annotation on crawled data, and trigger a workflow to investigate potential suspects.

Benefits

• Automation and AI-enabled big data analytics led to reduction in manual effort to the tune of $100k in annual labor costs.
• Risk mitigation and improved adherence to compliance and regulatory requirements.