Financial Crime Buster Analysis Template for TIBCO Spotfire®

This Spotfire template guides the user through the tasks of adhoc data discovery, supervised model creation and unsupervised model creation to build a strategy for combating financial crime.

Compatible Products

TIBCO Spotfire®

Provider

TIBCO Software

Compatible Versions

Tested on Spotfire 7.7 / 7.8, TERR 4.2 and CRAN packages randomForest 4.6-12, ROCR 1.0-7, rjson 0.2.15, RCurl 1.95-4.8

License Details

License

TIBCO Component Exchange License

Overview

The approach used in this template for fighting financial crime places machine learning at the center of the crime detection system. Machine learning models use historic data to learn how to spot risky or abnormal behavior exhibited by transactions, clients, suppliers, or other players. It uses two types of models: Supervised learning algorithms, that tell us how similar to past fraud a new transaction is and Unsupervised learning algorithms, that tell us how odd a new transaction seems when compared to past transactions.  The first model guarantees accuracy, the second the ability to adapt to changing realities.

Whitepaper

Read the whitepaper on Busting Financial Crime with TIBCO

License Details

Release(s)

Release v1.3

Published: May 2017

  • TERR scripts in the SendToStreamBase_CC_Supervised and SendToStreamBase_CC_UnSupervised data functions now facilitate debugging of the real-time scoring function.  See the embedded scripts for details.  
  • Now handles previously unseen categorical values when scoring the random forest model. Those values are now labelled "Unseen".
  • UI Improvements

Release v1.2

Release v 1.1

Release v1.0

Reviews (3)
5
PJ Evrard 6:40am 10/13/2016

Great material, easy to adapt to different contexts, just by replacing the data !

5
Mark Palmer 9:24am 10/07/2016

Fraud detection is a very important use case for TIBCO customers, and it's great to see Ana's leadership in this space. Make sure to read her excellent whitepaper, which is linked on this page. Also, for those of you who are interested in fraud and how the TIBCO platform might integrated with Spark, SparkML, TERR, and H20, and StreamBase, check out the Spark Accelerator: 

https://community.tibco.com/modules/accelerator-apache-spark

We're doing a lot of work at TIBCO with customers to integrate these two elements of the Fraud Detection solution. Stay tuned for more community updates here.

5
Ana Costa e Silva 1:48pm 10/03/2016

Don't think I am very impartial here :) But personally, I love it :)

Busting Financial Crime with TIBCO®

 

Introduction

Existing financial crime solutions suffer from two problems:

  1. Many false positives
  2. Long investigation times

The curse of existing crime fighting solutions for financial institutions is that they are black boxes which require hefty consultancy fees to update.

At TIBCO®, we can improve your situation in a number of ways:

  • Apply machine learning to your historic data in a fully transparent approach
  • Leverage your big data without moving data across and without coding!
  • Make machine learning uncomplicated so your business people can interact with it directly
  • Compare new models with existing ones to make sure you always improve
  • Do what-if analysis to adjust your investigative efforts to the size of your team and vice-versa
  • Understand how good a model is, which KPIs contributed most to it, track model versioning
  • Deploy models ultra fast with Streambase
  • Keep track of all alerts and all investigative actions taken on them, such that everything is auditable at any time in the future
  • Justify why any transactions reiceived a certain treatment
  • Verify that all investigators are following expected procedures, identify bottlenecks, manage workload

 

Why it matters and how it works

 (4.5 minutes)

 

Customer Successes

 

Where to go to learn more

  • Read the TIBCO blog entry: TIBCO’s Accelerator for Financial Crime Was Just Published and It’s Not a Black Box
  • Read the white paper: PDF iconBusting Financial Crime with TIBCO - the white paper
  • Download the free TIBCO Exchange template, TIBCO Spotfire Template for Busting Financial Crime, load your own data and understand financial crime within your organisation, be it AML or insurance claim fraud, credit scoring or trading floors. 
  • Download the TIBCO Financial Crime Accelerator: TIBCO's Financial Fraud Detection Accelerator: download the remaining components and respective instructions of TIBCO's Insight to Real Time Action platform as applied to Financial Crime Fighting, so that your organisation has access to all the knowledge necessary to set up the infrastructure to do this yourself.
  • Play with the Spotfire template using a free trial Cloud Account (get one here):
    1. A cross-industry AI Streaming Machine Learning tutorial aimed at either business users wanting to set up a machine learning strategy for their business, or advanced data scientists wanting to put their models into production in real time (download or just play). Learn how to adapt it to maverick lot, AML, churn, credit scoring, fraud, claim management, anytime you need to separate one group of cases from the rest.
    2. A supervised learning template that uses different models at once to allow users to choose the best (download).
    3. A network chart template that allows users to enter relationships between potentially criminal nodes and spot other members of their crime ring. Forensics on potentially huge data volumes (download or just play).
Go to Spotfire FSI page Go to Spotfire Wiki Home page

View the Wiki Page