Paranoia and Paradox — Using Speech Analytics Redaction to Lessen Security Risks


Share on LinkedIn

There’s a contradiction between consumer data and the consumer experience. Customers are increasingly paranoid about the security of their personal information when it’s in the hands of companies. However, companies need this information to provide customers with the streamlined and personalized experiences that consumers have come to expect. The marketing and sales sides of the business understand that access to data is the catalyst for growth. It helps the company to explore new markets, find previously hidden profit centers, abandon lagging products or services, and proactively adjust tactics based on predictive analysis. But consumers are worried about data exposure.

Consumer paranoia about the loss of their personal data is not an unreasonable feeling. Breaches at Equifax, Uber, Yahoo!, and Verizon not only negatively impacted the affected customers, they also further eroded the public trust. The need to protect data and preserve a brand image is conflicted by the increasingly central role that data plays in the modern organization. “Companies run on data” as the saying goes, and they need information to perform predictive analytics, customer sentiment analysis, and other initiatives that simply aren’t possible without ready access to information.

How can companies tackle this contradiction in a way that will protect privacy without removing the ability to offer personalized experiences? Speech analytics technology offers a streamlined solution with platforms that automatically redact any sensitive personal information to ensure credit card numbers and other sensitive information are not stored, and therefore not at risk.

The Role of Speech Analytics in the Modern Business

Speech and engagement analytics platforms capture voice, email, and chat conversations and transform them into structured data that can be searched, categorized, and patterned. Access to such content provides centers with unparalleled insights to customer information, from the overall mood of the entire customer base, to data about the empathy displayed by individual call center agents.

These solutions are typically utilized in a call center setting. Hundreds or thousands of agent-to-customer calls happen daily in a center, and the content of the calls represent a gold mine of valuable information. Speech analytics tools can transcribe and store every word from a conversation, and then open that data to analytics that can find trends. Advanced tools can gauge sentiment and tone, and help management to spot potential problems that are causing spikes in calls.

The data risk with such high-powered call analytics comes when call centers are taking sensitive personally-identifiable information from customers such as social security numbers, credit cards, and birth dates. Firms that manage sensitive customer information sometimes overlook their recorded calls as a source of data that demands Payment Card Industry (PCI), or other regulatory compliance. The PCI Security Standards Council has even produced official guidelines for the management of recorded call data — clearly stating this type of content deserves full protections.

Call recordings are subject to the same rules as any other method of capturing and storing confidential information. Access to call recordings and transcripts for purposes of agent performance management or customer experience insight, particularly if shared more broadly across the organization, creates an immediate risk for data breach. That data needs to reside somewhere, and its very existence makes it a target for hackers and the criminal (or simply foolish) actions of internal staff.

The Promise of Data Redaction

Speech analytics with automated redaction is a business technology that can show the way forward for responsibility and responsiveness. As a data tool that stores information to avoid frustrating customer service calls, its purpose is to utilize information about language patterns, emotional inflections, and keywords to deliver the smoothest possible experience. By utilizing advanced redaction software, speech analytics technology can automatically scrub any recordings of sensitive customer information, such as social security numbers, credit cards, and the like.

Redaction works by replacing such information as a credit card number with a generic term and removing that data (muting) from the call recording. If a customer provides this data during a call, the speech analytics system dynamically recognizes the information and replaces the actual numbers with “Redact” or some other standardized non-identifying language, and inserts silence in that portion of the call recording. Redaction is even better than encryption because it entirely eliminates the storage of such sensitive information. Even in cases of hacking or accidental exposure, the sensitive data doesn’t exist. Other approaches require agents to manually pause recording or enter a specific field within their sales order system before accepting the customer’s information. This is unreliable and requires too much manual concentration, compared to redaction which simply acts on data.

By performing such redaction, contact centers can actively manage their exposure to harmful data breaches. This approach allows for sharing of customer interaction insights to departments such as sales or marketing, resulting in better business intelligence and faster time to decisions and action.

Redaction is a powerful tool because it removes the information — hackers can’t steal what’s not there. It’s become critical for companies to enhance access to quality information while also lessening the impact of any data breaches. Advanced speech analytics tools from top-tier providers offer such a model that allows deeper engagement with customers and less risk exposure for the company.

Scott Kendrick
Scott has 20 years’ experience in software product management, design, and marketing for everything from shrink-wrap consumer applications to enterprise cloud solutions. He introduced the tag-line “Listen to your customers – Improve your business” which is both something he passionately embraces in marketing and product management, and how he articulates the benefit CallMiner Eureka brings to market. Prior to CallMiner Scott was Sr. Director of Global Product Management at MIVA (an internet search marketing company), and Director of Product Management and Marketing for the New Ventures divisio


Please use comments to add value to the discussion. Maximum one link to an educational blog post or article. We will NOT PUBLISH brief comments like "good post," comments that mainly promote links, or comments with links to companies, products, or services.

Please enter your comment!
Please enter your name here