There are several AWS services that implement anomaly detection and could be used to defeat fraud, but let’s focus on the following three:
When trying to detect fraud, there are two high-level challenges:
Scale
The amount of data to be analyzed. For example, each call generates a call
detail record (CDR) event.
These CDRs include many pieces of information such as originating and
terminating phone numbers, and duration of call.
Multiply these CDR events times the number of telephone calls placed each day
and you can get an idea of the scale that operators must manage.
Machine Learning knowledge and skills
The right set of skills to help solve business problems with machine learning. Developing these skills or hiring qualified data scientists with adequate domain knowledge is not simple.
Amazon QuickSight is a fast, cloud-powered BI service that makes it easy for
everyone in an organization to get business insights from their data through
rich, interactive dashboards.
With pay-per-session pricing and a dashboard that can be embedded into your
applications, BI is now even more cost-effective and accessible to everyone.
However, as the volume of data that customers generate grows daily, it’s
becoming more challenging to harness their data for business insights.
This is where Machine Learning comes in.
Amazon is a pioneer in using Machine Learning to automate and scale various
aspects of business analytics in the supply chain, marketing, retail, and
finance.
ML Insights integrates proven Amazon technologies into Amazon QuickSight to provide customers with ML-powered insights beyond visualizations.
In this lab, we will demonstrate how a Telecom Provider with little to no ML expertise can use Amazon QuickSight ML capabilities to detect fraudulent calls.