Singapore: +65 6384 5411
Sydney: +61 2 9025 3976
Perth: +61 4 0662 5401

Compliance Quotient

Latize Compliance Quotient improves financial institutions’ ability to detect, time to investigate and intelligently reduce false positives in suspicious transactions and activities associated with Anti Money Laundering (AML) and Countering the Financing of Terrorism (CFT) practices.

The Problem

Current silo-data source and rule-based systems give rise to a high number of false positives and labour intensive flag disposal process. Analysts struggle to get sufficient information and complete understanding to make well informed decision within limited time frame.

  • Ever-escalating time required for analyst to dispose of flags due to fragmented information
  • Questionable level of accuracy and consistency of flag disposal decisions
  • Time consuming SAR/STR report generation
  • Rigid and non-adaptive rule-based engines produces high numbers of false positives

Our Solution

Ulysses, our revolutionary augmented intelligence platform, automatically brings together all relevant data required for decision making - across multiple sources, internal and external. We believe Compliance Quotient can reduce fraud - or any other illegitimate activities – at a much lower cost, without disrupting the customer’s banking experience.

By seamlessly linking and combining information from external data sources (such as social networks and blacklists) with ‘learnt data’ from suspicious transactions, and incorporating unstructured data such as e-mails, counterparty contracts and other text-based documents, Compliance Quotient turns all of your Big Data into a usable knowledge base.

With an intuitive and user friendly visual interface into this diverse data, Compliance Quotient enables the monitoring team to intuitively browse across voluminous, complex, and previously fragmented data sets.

Semantic graph based machine learning algorithms will then be used on this knowledge base to reduce the number of false positives flagged by existing fraud surveillance and other monitoring systems. The automatic feedback loop based on confirmed false positives ensures ongoing learning and evolution of the algorithms, minimizing false positives over time.

Analysts will have a single view of a transaction, event, person or whatever is of interest, showing all attributes, activities, and interactions in a manner which is readily understandable. In addition, users can easily select the types of relationships and degree of separation to explore the possible relationship between entities. This enables the analyst to identify indirect relationships and isolate suspicious activity that would be difficult to uncover by studying scattered information independently.