Financial Fraud Detection Accelerator
Identify potentially fraudulent activities in a high-frequency transaction stream using TIBCO's Financial Fraud Detection Accelerator. Build supervised and unsupervised models and hot deploy these on the event processing platform. Score transactions in real-time and raise cases for investigation when potential fraud is detected.
TIBCO Spotfire® TIBCO® Enterprise Runtime for R (TERR™) TIBCO® Live Datamart TIBCO StreamBase® TIBCO ActiveMatrix® BPM
TIBCO ActiveMatrix BPM
TIBCO Live Datamart
TIBCO LiveView Web
TIBCO Spotfire Server
TIBCO Spotfire Analyst
TIBCO Enterprise Message Service
TIBCO Component Exchange License
The 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 dataset. Models are developed using the R programing language and then hot deployed to TIBCO StreamBase for evaluation at runtime 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 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.
The DevZone Forums are a traditional threaded discussion service subscribed to by Accelerator Developers, Practitioners, and Customers with a shared interest in the TIBCO Event Processing and Streaming Analytics platforms. Accelerators are provided as fast start templates and design pattern examples and are supported as delivered. For all questions concerning Accelerator use and implementation, please open a new discussion in the DevZone forum here.
There are currently no reviews for this content.
Why not be the first to review it - click here to login
Financial Fraud Detection Accelerator
The Financial Fraud Detection Accelerator illustrates a reference architecture that shows how Predictive Analytics, Streaming Analytics and Business Process Management can collaborate to support the full livecycle of end-to-end fraud detection in financial organizations. The accelerator includes a demonstration that shows an Anti-Money Laundering use case.
This video explains why detecting financial crime is important and how it works.
January 13 2017, release of Financial Fraud Detection Accelerator 1.0.0
The combination of legislation, market dynamics, and increasingly sophisticated fraud strategies is requiring institutions to be increasingly pro-active in detecting fraud quicker and more effectively. Transaction surveillance helps to ensure orderly and trustworthy markets, where buyers and sellers participate because they feel confident in the fairness, transparency and accuracy of transactions.
Today’s dynamic detection systems need to be agile, scalable and intelligent.
- Agile to adapt to ever evolving compliance regulation.
- Scalable to deal with ever increasing transaction volumes.
- Intelligent to detect increasingly sophisticated fraud patterns, and also to reduce false positives in the alerting stage.
Coupled with the detection system, an essential component is Case Management. Taking an alert from when it is raised, through the investigation stage and if applicable on to the regulator requires a capable and integrated Case management tool, which can capture all the inputs from historical data, surveillance analyst notes and transaction log extracts.
Fraud detection spans many different domains. Some of these include:
- Anti-money laundering (AML)
- Trade surveillance
- Credit/Debit card monitoring
- Health insurance fraud
- Insurance fraud
- Online operations
In all cases what they have in common is a relatively high frequency of transactions, at which any given time a certain percentage can be classified as fraud. This percentage will vary greatly by market, industry, value, and other parameters. But the key to surveillance systems is to maximize the number of fraudulent transactions that are identified, while minimizing the number of false positives to come up with an optimal system both from an operations and financial standpoint.
Benefits and Business Value
Regulation and potential fines aside, it is in the best interest of the market participants to adopt and mature some form of surveillance that enhances visibility and transparency while assisting to minimize risk and avoid losses due to rogue trading.
The accelerator brings the following key benefits:
Faster time to resolution
- Data discovery, statistical model creation and integration within a single tool
- Dashboards that integrate data across databases (historical and reference data) alongside information from the real-time processing, users can filter, slice and dice, zoom in and out of data in order to determine if the alert needs further investigation or can be discarded as a false positive
Accelerate the adoption and rolling out of surveillance
- Surveillance projects can span multiple assets, data and scenarios that can go from monitoring abuse in cash equities to complex schemes involving foreign exchange (FX) and derivatives
- With connectivity to over 150 options, including Bloomberg, BM&FBovespa, Currenex, EBS, FIX, FXall, Hotspot, Interactive Data, and Thomson Reuters, all your data feeds can be included
- A graphical flow based development reduces complexity and increases collaboration
Flexible Surveillance Scenarios
- The predefined abuse scenarios adhere to the specifications published by regulators; however it is common that each institution needs to tailor not only the thresholds that trigger the alerts but also exclude certain events from the analysis altogether
- Perform correlation to detect complex potential abuses on one asset type attempting to influence a related instrument of another type.
The accelerator include a demonstration of fraud detection using a credit card transaction dataset that is analyzed against both a supervised and an unsupervised model to produce a score that indicates the probability of fraud, and another score that show how the transaction deviates from what could be considered normal, also known as oddity.
Other demo scenarios will vary from this. For example trade surveillance will differ greatly from insurance claims and credit card transactions. However the accelerator is intended to show a design pattern for detecting fraud using a combination of event processing and analytics rather than provide a series of concrete rules for doing the detection. The agility of the analytics and event processing platforms allow customers to modify the framework quickly and easily to adapt to other scenarios.
TIBCO software products and versions used:
|TIBCO ActiveMatrix BPM||4.1.0|
|TIBCO Live Datamart||7.6.6|
|TIBCO LiveView Web||1.1.3|
|TIBCO Spotfire Server||7.7.0|
|TIBCO Spotfire Analyst||7.7.0|
|TIBCO Enterprise Message Service||8.3.0|