Fraudulent activity. Suspicious transaction. Discrepancies.
These utterances all point towards the five-letter nemesis: fraud.
Fraud has long been an issue in many industries, and dealing with it is anything but a joyride. The headaches, confusion, hopelessness, and major losses that follow a fraudulent attack continue to plague many organizations.
Cue our latest webinar held on May 24th: Building an Online Anti-Fraud Open Source Monitoring Program. In this webinar, Tyson Johnson, BrightPlanet’s Vice President of Sales and global fraud/loss thought leader, discussed how thinking differently about open source data can help prevent fraud.
Combatting Fraud and Online Counterfeiting with Open Source Intelligence Tools
Through our findings, we’ve discovered that hindering fraud and online counterfeiting requires smart solutions. Primarily, these solutions come down to focused data harvesting and real-time alerts.
In this webinar, we looked at building an online anti-fraud open source monitoring program and then really dug deep into how we use open sources as well as gave some practical skills to attendees.
There are many different ways to think about open source data and how to use it for fraud programs.
Data Harvesting to Inform Insights
At BrightPlanet, we have a fairly well-defined process for how we work with clients. Harvesting data is the very first stage. We then curate that content specific to the data initiatives that the clients have identified, such as anti-fraud initiatives. That curated content then helps us generate insights.
This webinar showed attendees why they need to start an internal conversation about creating their own strategies and methodologies for generating these insights.
Data harvesting is a large undertaking. On the web, data is everywhere, in everything, all the time. Take the web as many know it today: Google. Search engines such as Google, Yahoo, and Bing are all capable of accessing the Surface Web, such as websites.
Take one step deeper and you have the Deep Web, which are again websites the popular search engines may access. However, content in the Deep Web is hidden behind those initial main pages and additional querying is required to obtain that specific information.
Then, of course, there is the Dark Web. The Dark Web is the obfuscated part of the web where you need to look at data through a TOR browser. This data is not even in the same location day after day, so it’s quite difficult to find, locate, and maintain.
Now we can tell you from our experience of working in data harvesting and open sources for over 15 years that the Deep Web is the absolute largest body of information available. The Surface Web comes in second, followed by the Dark Web.
Curate Data with Open Source Intelligence Tools
When looking into fraud for this webinar, we looked at credit card data that is being sold online. Let’s look at it as an anti-fraud initiative for financial institutions and card-issuing organizations.
Finding information online that will show an exposed card and potentially identify breach events is a very trying task if you want to do so manually. And manual information gathering produces data in many different forms and ways; there’s no structure to the content that you’ll see.
Here at BrightPlanet, we like to harvest the content and then run it through a rules-based entity extraction process that sorts the data into easily-digestible rows and columns of structured data. This allows for viewing credit card numbers by the date or time of exposure, by the brand, or by the bank that it was assigned to. Then all of the other data is also structured and relevant to each individual field. You are then able to run analytics or relationship mapping against that type of data.
Develop Fraud Protection Insights
To develop the insights, we want to be able to help a client either generate their own analytics dashboards or be able to pull our data through an API and then plug it into existing dashboards or analytics engines.
Being able to harvest, curate, and then generate the insights so that you can ask questions of the data and be able to then leverage the data for your anti-fraud initiatives is the whole process that we work with our customers on. And as a managed service, our job is to be your 24/7 support and your behind-the-scenes harvest and curation experts to really help you build this out.
So what everyone needs to do is start thinking differently. Think about a particular risk or a fraud risk that you’re managing today and think, what outputs do we want to obtain from the data? What is the issue we are hoping to gain insight on? And what does insight from the data look like?
Download the Open Source Anti-Fraud Webinar
Want to learn more about using anti-fraud open source intelligence tools using focused data harvesting and real-time alerts? Watch the full webinar recording, which goes much further in-depth and delivers tangible skills to use in real-time.
Start thinking differently to stop fraud in its tracks. Download the webinar today.