Detect Fraud in Your Contact Center

Learn how to use the VBG Platform to detect fraud in your contact center.

Image Description

Detect Fraud in Your Contact Center

For companies with a consumer-facing retail operation, a major source of fraud in the contact center is a criminal pretending to be a new customer. The criminal uses a false identity to extract benefits, such as getting a new device under contract, and then abandons the contract and is not to be found. The criminal benefits to this behavior and similar activities such as account takeovers are so tempting that criminals organize into groups to systematically and repeatedly defraud a company, altering tactics whenever the company erects a new defense.

Voice Biometrics technology offers a powerful, undetectable defense that companies can implement at their contact center perimeter. Using recordings in the contact center, companies can apply voice biometrics to compare voices of new customers with voices from known fraudsters as well as existing customers. If the voice of the new customer matches a known fraudster or an existing customer with a different identity, then the company can mark the conversation as highly likely to be fraudulent.

Voice biometrics, like fingerprints and iris scans are not 100% perfect. Some fraud will still slip through and some false positives will still occur. But, if a majority of the fraud is correctly detected in advance that would not be otherwise detected, the reduction of fraud losses can be dramatic.

How Does It Work?

Fraud Detection solutions that leverage voice biometrics work by using the power of NaturalSpeech™ passive voice biometrics. NaturalSpeech™ constructs voiceprints of individuals from either an active conversation between a caller and agent, or a post-call recording of their conversation. The process of constructing a voiceprint from audio is a process called enrollment. Once an individual is enrolled, you can gather new speech samples from the same (or a different) person and request NaturalSpeech™ to compare the new speech sample against one or more voiceprints to see if a match occurs.

As an example, if you know that a specific prior phone call was fraudulent, and you have the recordings of the fraudster's voice, you can enroll the audio of this recording and store it in a VBG "blacklist" database for subsequent analysis. This is depicted in Figure 1 below. Then, as new customer calls come in each hour, or or each day, or however frequently as you wish, you apply NaturalSpeech™ to compare recordings from new customers to voiceprints in your blacklist database. This is depicted in Figure 2 below. NaturalSpeech™ gives you a score that indicates the likelihood of a match. A high score indicates potential fraud, thus giving you the opportunity to act before fulfilling what may be a fraudulent order.

Voice Biometrics Group Enroll and Detect Fraud

A critical point to understand is that the audio sent to the voice biometric engine must be from only one speaker, the person you want to enroll or the person you want to compare. Many contact centers can only store call center recordings in a mono format where both the caller and the agent are contained in a single track. Because the agent audio is also in the recording, the recording cannot be used to enroll the caller.

Software exists that attempts to take recordings with multiple speakers in them and separate them into different recordings for each speaker. This is called "speaker diarization" sofware. And while more recent deep learning algorithms are helping to improve the accuracy of diarization, we believe it does not yet work reliably enough for the purposes of automated fraud detection using voice biometrics.

What you need from your contact center recorder is a stereo recording where each speaker is in a different track but perfectly synchronized, as depicted in the figure below. In this format, you will be able to strip the track of the caller from the stereo recording to send to the voice biometric engine. If your contact center does not have stereo recording capability, VBG has several partners who may be able to assist you.

Voice Biometrics Group 2-Track Passive Recording

How Much Does It Cost?

The cost to deploy voice biometric technology for fraud detection depends on: (a) the number of voiceprints in the fraudster database that need to be compared, (b) the amount and content of the speech sample, and (c) the response time needed to meet your business objectives. Larger blacklist databases, longer audio content, and shorter turn-around times mean that more equipment will be required for parallel processing. This results in higher costs. Thus, pricing a system depends greatly on your situation and will inevitably require a custom quote.

As an example, imagine a call center conducting retail sales with the following parameters:

  • After you take an order, you have 24 hours before fulfilling the order
  • You receive 500 new customer calls per day
  • You have 100 known fraudsters in your fraud database
  • You will use a VBG hosted version of VBG Enterprise™

For this scenario, you need to compare the 500 new customers each day against the 100 known fraudsters, all within 24 hours. Running 500 * 100 comparisons = 50,000 total comparisons withing 24 hours. This amount of processing easily falls within a range where we do not need to add dedicated servers. And using VBG's cloud means fast setup and no installation fees. The pricing at this volume of transactions and voiceprints is on the order of 10 cents for each comparison, plus $15 per month per fraudster voiceprint. The total cost is therefore $50 per day for the comparisons, totaling approximately $1,500 per month for transactions, plus $1500 per month for voiceprints, equaling $3,000 per month, or equivalently $36,000 per year. This is only indicative pricing. Volume discounts and on-premise licenses are available to adapt pricing to your situation.

As another example, perhaps you not only want to compare a speech sample against an existing database of fraudsters, but you also want to detect new fraudsters. New fraudsters will appear as a repeat new customer. So you will not only maintain a blacklist database for fraudsters, but you will also maintain a rolling database of new customer voiceprints (perhaps for all customers who are new within the last two weeks). VBG's technology can tell you if a new customer under a specific name is also a new customer using a different name within the last two weeks. Maintaining a rolling database of new customers increases costs but also adds a layer of fraud prevention on top of fraud detection.

Finally, another option that adds complexity, but may be highly desirable, is to use live audio during the call as the comparison against the fraud database rather than waiting to process the recorded call after the fact. With live audio, you then have the possibility of sending screen pops to the agent screen and transferring the call to a special agent who knows how to handle a caller is highly likely a fraudster. This option is entirely possible but requires tighter integration into the call center part of the contact center.

Get Started

If you have a business susceptible to fraud in the contact center, the next step is to gather as much information as possible to help you prepare to use voice biometrics. The following list of questions will be an excellent starting point:

  • Are my recordings in a format where each speaker is in a different audio track?
  • Do I have recordings of the fraudsters?
  • How many fraudsters are recorded?
  • How many new customers order through the call center each day?
  • How much time is available to determine if fraud occurs before fulfilling an order?
  • How important is it to prevent fraud by analyzing new customers not currently known to be fraudsters calling in multiple times under a new identity?
  • Do I need the voice biometric system located in my data center for security or privacy reasons?
  • How important to me is it to analyze live calls for fraud rather than processing call recordings after the fact?

Once you've gathered this information, scroll below and fill out our Contact Form. And let us know a convenient time for an discussion ... we'll get back to you quickly and look forward to assisting you.

Want to Read More?

All Documents in this Series

Click on the title of the document you want to read next

Contact Us

Do You Have Any Questions?

Please let us know how we can help you and we'll respond promptly!

Image Description