Onboarding

The beginning of a business relationship with a customer is an essential point to determine the risk level it presents to the Bank, and based on it, determine the next steps for mitigation:

Black lists: Module that allows the Microfinance Institution to analyze whether there are any matches of the data of the customer, either a natural person or a legal entity, with various international lists, like Negative News, OFAC, UNO, PEPs, and 450 other global lists, as well as with internal lists that the institution may have.
The Sentinel service provides more than 1 million PEP`S of 14 different types, with 3 levels in more than 240 countries. In addition, it classifies almost 50 risk events: abuse, kidnapping, fugitive, fraud, murder, theft, people trafficking, with the definition and classification according to the prevailing risk stage: accused, suspect, arrested, in trial, sanction, and others.

Risk Customer: The Sentinel risk matrix makes it possible to configure completely flexible parameters in various qualitative or quantitative factors that produce a risk score for the customer, based on the regulations of each country and on best practices. This score is recalculated automatically by the system, maintaining the history of all the variations suffered throughout time. The system allows the definition of up to nine risk levels.
The customer risk can be determined in real time during the onboarding process, making it possible to set up stricter procedures to accept the relationship, and subsequently analyze this relationship as a Microfinance Institution customer.

Customers, Employees, and Providers Profiling: Sentinel allows the generation of different criteria that make up the profile. This information is traditionally obtained from the Know Your Customer, Know Your Employee, or Know Your Provider forms. Increase in the activity expected in the profiles defined generates exceptions that are dealt with by those responsible.

Monitoring

Monitoring the different events performed by the customer, the employee or the provider is essential to discover unusual behaviors that could pose an asset laundering risk. Sentinel has a set of tools aimed at its early prevention and detection:

• Rule-based models: The system includes a rule editor that makes it easier for the user to build models grouping conditions, and containing lists, among others.
• Statistical behavior: It allows the generation of individual profiles for each subject of analysis (customer, financial product, etc.), defined as statistical indicators based on the transactional behavior of each of them. These profiles can be used as input when configuring the rule-based detection models.
• Dynamic behavior patterns: It is a new proprietary technology of Sentinel that allows the dynamic definition of the usual profile of the customer and of the population it belongs to. In this way, the system generates an alert if the behavior detected is “unusual” for the customer, or if it is “atypical” for the population it is a part of.
• Relationships Analysis: It allows the discovery of hidden patterns and relationships graphically, facilitating the investigation processes, as well as the detection of organized crime networks. By analyzing how money flows among different accounts and complementing this task with analysis of different points in time, the investigator can easily detect different laundering typologies.
• Predictive models based on “Machine Learning”: Sentinel Predictions provides a visual design environment to build anti-money laundering predictive analysis. It provides a complete library of learning algorithms, both supervised and unsupervised, data preparation and exploration, model validation and assessment tools.It also provides a powerful “Model auto-generation” capability that allows Sentinel to create and train multiple models automatically, compare their results, and provide the user with the possibility of determining which it wants to establish in a production environment. It is no longer required to be a Data Scientist or an expert in mathematics or statistics to use the most advanced “Machine Learning” techniques.
• Processes: Sentinel enables the automation of tasks and workflow activation based on the events generated by the system. For example, if a customer risk rating changes from medium to high, it is possible to establish an enhanced due diligence process that requests the customer executive to visit the customer and to apply a relevant form, which will be further reviewed by the Compliance Unit.

Investigation

Sentinel enables centralized or decentralized monitoring from the anti-money laundering perspective.

In a decentralized approach, the alerts or exceptions of the customer are transferred to its account executive, branch manager, or his delegate, for the first due diligence steps. In this case, the Compliance Unit acts as the strategist in the definition of models and risks for the institution, as well as in the more advanced states of the process, but in the initial operation and stages other Microfinance Institution areas are involved. Sentinel offers all the tools required for the follow-up and control when this approach is used.

On the contrary, with a centralized approach, the analysts of the Compliance Unit are responsible for reviewing the unusual activity and of all the process stages.

Case Management

Once the analyst reviews the activity that the system has suggested as unusual, it can generate cases to follow-up on the transactions and to record all the actions taken during the investigation process.

The investigation case is the digital file used to track the entire management process of the unusual activity of the customer:

• Review request of the Know Your Customer, Employee, or Provider profile
• Change in the investigation status, based on the workflow
• Actions carried out by the analyst
• Detail of the transactions reviewed
• It makes it possible to store attachments related to the case

Reports and Control Boards

• Sentinel enables the generation of regulatory reports that are sent to the supervising entity
• The system has a powerful tool for data discovery and information analysis. Its main characteristic is that it is oriented to end users without technical knowledge, who can design their own reports and dashboards, schedule their execution, and send them automatically to different emails, if desired
• It has pre-determined reports
• It allows the end user to create reports, using the different Sentinel data sources and fields
• The reports can be private or public so that other users can access them
• The generation of groups, filters, field order, and date range definition is enabled to display the information
• Ability to export the reports in multiple formats, including Excel, CSV, PDF