TIBCO Fraud Detection Accelerator helps you identify false positives by using machine learning. The coalition of the legislation, market dynamics and the increasingly sophisticated fraud strategies requires you to be proactive in detecting fraud quicker and more effectively.
Dynamic detection systems need to adapt to the evolving compliance regulations, scale to deal with growing transaction volumes, detect sophisticated fraud patterns and reduce false positives.
The combination of the predictive analytics, streaming analytics, and business process management gives a powerful and cost effective system for detecting fraud. TIBCO Fraud Detection Accelerator represents a new approach to how TIBCO engages the customer ecosystem. Depending on the use case, the TIBCO Accelerators include the event driven rules in
- IoT streaming analytics with StreamBase
- Alert templates
- Predictive analytics built in R
- Spotfire analytics and dashboards
- Integration with BusinessWorks
- Case management with TIBCO ActiveMatrix BPM
Financial Fraud Detection Accelerator
Recognize potentially fraudulent activities in a high-frequency transaction stream using TIBCO’s Financial Fraud Detection Accelerator. Build supervised and unsupervised models and deploy these on the event processing platform. Score transactions in real-time and raise the cases for investigation when potential fraud is detected.
The TIBCO Fraud Detection Accelerator uses TIBCO Spotfire Analyst to guide data professionals through the process of developing both supervised and unsupervised models to detect probability of fraud and transaction oddity from a known data-set.
Models are developed using the R programming language and then hot deployed to TIBCO StreamBase for evaluation at run time using TIBCO Enterprise Runtime for R.
When a transaction is scored it will either pass, or be flagged as probable fraud, odd transaction, or both. When this occurs the event processing platform raises an alert and creates a case in the TIBCO ActiveMatrix BPM, that facilitates the investigation of the potential fraud. Investigators are then provided with the analytics tools tools to help determine whether or not a transaction is actually fraud or not all within the fully functional case management environment.
- Faster Incident Resolution
With the data discovery, statistical modeling, and aggregation within a single tool, you can create dashboards that pull from multiple databases and real-time information. Users can filter, slice and dice, and zoom in and out of the data to determine if the alert needs further investigation or can be discarded as a false-positive
- Faster Surveillance Deployment
The Surveillance projects can span multiple assets, with data and scenarios that range from monitoring abuse in cash equities to complex schemes involving foreign exchange derivatives. With association to over 150 options, all your data feeds can be included using the graphical flow development that reduces complexity and increases collaboration.
- Flexible Surveillance Scenarios
You’ll want to tailor the thresholds that trigger alerts and exclude certain events from the analysis altogether. Perform correlation tests to detect complex potential abuses on one asset type so you can determine the alerts and performance for related assets. This helps to maximize the identification of anomalous data points and minimize false-positives.
- Supervised and Unsupervised Models
Data is analyzed against both supervised and unsupervised model to produce a score that indicates the probability of fraud and another score that shows how the transaction deviates from what’s normal, also known as an oddity.
- Real-time Transaction Scoring
When a transaction is scored, it either passes or is flagged as a probable fraud, an odd transaction, or both. By scoring transactions as they happen, you can respond to the raised alerts provided by an event processing platform and create a case that facilitates the investigation of potential fraud.
- Case Management
With a capable and integrated case management tool, you can take the alert from when it is raised, through the investigation stage, and if applicable, onto the regulator. Take the inputs from historical data, surveillance analyst notes, and the transaction log extracts to determine what’s fraud and what’s not.
- Event Processing
Detect fraud by using a combination of event processing and the analytics rather than a series of concrete rules for detection. The acuteness of these platforms allows you to modify the framework quickly and easily to adapt to the other scenarios.
- Multiple Use Cases
TIBCO Fraud Detection Accelerator spans many different domains including anti-money laundering, trade surveillance, credit/debit card monitoring, health insurance fraud, insurance fraud, and online operations.
- Rigorous Auditability
Justify to regulators the decisions about what events were determined to be fraud or not and what actions were escalated or not. Show consistency over time, reasons for the changes in approach, and documented changes and approvals.