This QA first appeared in Data Science Briefings, the DataMiningApps newsletter as a “Free Tweet Consulting Experience” — where we answer a data science or analytics question of 140 characters maximum. Also want to submit your question? Just Tweet us @DataMiningApps. Want to remain anonymous? Then send us a direct message and we’ll keep all your details private. Subscribe now for free if you want to be the first to receive our articles and stay up to data on data science news, or follow us @DataMiningApps.
You asked: How do you see the area of fraud analytics changing in the near future?
We think fraud analytics will substantially gain in importance because of the new technologies which are being introduced on an on-going basis. Just think of the Internet of Things (IoT) as an example where we will connect various things such as electronics devices, sensors, software, IT infrastructure, etc. into one huge network. It speaks for itself that the amount of data generated will be enormous which offers an unseen potential for analytical applications. As with all new technologies, this will create both new treats as well as emerging opportunities from a fraud perspective. Fraudsters might force access to web configurable devices (e.g. Automated Teller Machines (ATMs)) and set up fraudulent transactions.
Another example is device hacking whereby fraudsters change operational parameters of connected devices (e.g. smart meters are manipulated to make them under register actual usage). In terms of new opportunities, just think of telematics where the idea is to equip a car with a special device called black box which continuously monitors the driving behavior by gathering data and streaming it to the insurance provider. Examples of telematics data that are collected during each trip are: the distance driven, the time of day, duration of the trip, the location, the speed, harsh or smooth breaking, aggressive acceleration or deceleration, cornering and parking skills. This can then further be augmented with road maps, weather and traffic information. By carefully analyzing all these data elements, the insurance provider can substantially improve fraud detection. More specifically, when an insurance claim is filed, the facts provided can now be more carefully checked. E.g. was the driver respecting the speed limit? Did the accident occur at the claimed location? Did the driver brake in a timely manner? Was the driving behavior different compared to recent driving behavior, possibly suggesting a different driver or alcohol intoxication? Furthermore, using telematics data, it becomes possible to re-enact car accidents. This is not only handy to define who is at fault, but also to identify fake accidents resulting into fraudulent claims.
Remember, this is only one example of how fraud analytics will change in the (near) future!