Losses from internal fraud are estimated at 6.3 trillion dollars, representing a high risk factor for the operation of financial entities. The impact of these fraud cases is very strong, with an average loss per event of US$192, and 23% of the cases exceeding US$ 1 million in economic losses.
Additionally, one of the main problems is the time required to detect fraud and, consequently, the effective recovery. According to the ACFE* study, this period is 18 months.
*Association of of Certified Fraud Examiners
Sentinel is a specialized tool for internal fraud prevention in financial institutions. The analytical engines and various detection tools of Sentinel support the financial institution in internal control and security, preventing the use of employees of their work positions for their personal benefit by performing improper or illegal actions with the resources of the institution.
The transactions performed by an executive can be monitored by the system, generating analyses:
Rule-Based Models: The system presents a modern and entirely graphical rule editor that facilitates the construction of models for the user: it groups conditions, includes lists, multiple statistical conditions, and complex analysis patterns, among other features. Expert users also have the ability to use formulas on conditions, facilitating data manipulation and results of the rule.
Statistical Behavior: The creation of individual profiles for each executive is possible, defined as statistical indicators based on the transactional behavior of each of them. These profiles can be used as inputs to set up the rule-based fraud detection models.
Dynamic Behavior Patterns: The first risk filter for employees is of utmost importance to avoid future internal fraud cases.
Black Lists: Functionality that allows the entity to analyze multiple internal and external black lists.
Relationship Analysis: It enables the graphic discovery of hidden patterns and relations, facilitating the investigation processes and the detection or organized crime networks.
The ability to find relationships among very different data sources, like transactions, telephone logs, profile of employees, etc., enhances the great analytical capacity and the discovery of unusual situations.
The analysts have a query or viewer that enables them to view the unusual activity with multiple inputs for their decision-making process:
a. Filter by date range
b. Alert objective
c. Filter by alert status
d. Advanced filter
e. Transaction assessment scores
f. Behavior profile
g. Models of transaction alerts
The supervisors and analysts can have strategic control of the whole operation of the fraud prevention department by observing the following key indicators:
a. Pending alerts
b. Average attention time
c. Alerts flagged as fraud
d. Alerts referred to investigation
e. Alert resolution times
f. Goal fulfillment
Once the analyst reviews the activity that the system suggests as suspicious, he can generate cases that allow him to follow-up on the suspicious transactions and record all the actions that the user performs during the investigation process.
The investigation case groups the unusual transactions and also makes it possible to see all the historic behavior of the officer. It has a flow of the investigation statuses and allows the definition of a list of actions that will be performed by the investigator in charge. Files can also be attached to the case.
It is possible to have control of the investigations:
The system sets a “Timeline” of the investigation case, making it easier to view the history of the case of study.