Fraud Management with InterSystems IRIS

Organizations around the world lose an estimated five percent of their annual revenues to fraud, according to a survey of Certified Fraud Examiners (CFEs) who investigated cases between January 2010 and December 2011. Applied to the estimated 2011 Gross World Product, this figure translates to a potential total fraud loss of more than $3.5 trillion (source: https://www.acfe.com/press-release.aspx?id=4294973129).

The most efficient way to reduce frauds is to collect and unify the transactions, assets and target data to identify patterns, produce anti fraud reports and algorithms to validate the next transactions. In summary, we have some this principles to be followed:

	Ability to collect, enrich and unify data on targets and assets			Fluidity in the processing and exchange of data between systems, teams and internal and external information sources
	Multiformat and multi-model corporate database on targets and assets			Intensive use of Artificial Intelligence applied to the business context
	Collaborative work based on the findings identified by the automations			Rich composition of findings and dossiers based on flexible and well-grounded analytical artifacts

Before data platforms like InterSystems IRIS, the challenge was hard, see:

Expensive, closed and specialized Intelligence Systems Few data sources and little variety A lot of manual work Low collaboration capacity Low precision results Only experts were able to work

Open systems (R and Python), more accessible and broad Explosion of data sources and formats (Big Data) Automation of 70% to 80% of Intelligence work High collaboration capacity High precision results (advanced use of statistics and AI algorithms) Multidisciplinary and self-service team

InterSystems IRIS has a great data platform to do Anti fraud management, see:

The benefits are clear because with 1 product we can:

1. Collect data to analyze, create patterns and anti fraud algorithmns (R and Python) using IRIS Interoperability with BPL, DTL and Interoperability adapters and if something is special we can use Native API and PEX to do custom data adapters in Java, .NET or Python.
2. Apply rules and deduplicate the data using BPL, DTL, ObjectScript and Native API, with visual Interoperability orchestraction.
3. Store multimodel data and produce data results as networks, NLP, SQL, NoSQL and OLAP with InterSystems Database.
4. All this data can be consumed with AI algorithmns running with IRIS to predict and identify frauds. Is possible use IRIS IntegratedML (AutoML) to accelerate and improve anti fraud analysis.
5. Teams can produce dossiers and reports with the findings using IRIS Reports and IRIS BI and share all this with systems and people with User Portal, Report Server and IRIS API Management.

In other platforms you need to buy some products like SQL database, NoSQL database, Data Bus, ETL engine, Rules and Intelligence Server with Machine Learning support, NLP engine, Analytics, Report Server and API Management solution. The costs are high, but with IRIS is possible reduce these costs, because we have "all in one", see: