More and more organizations are looking to build in-house data science or AI teams to use emerging technology and techniques to harness the power of their data. With the growth of these internal data science teams, many companies are looking to gain greater control of all aspects their data programs to be more nimble and effective. If done correctly, this also provides more opportunities for creativity and experimentation with internal and external data. We scientists can bring a new level of insight to organizations. Turns out having scientists around is kind of cool. Please, don’t let the dazzle of our NASA space camp t-shirts, utter domination in quoting dystopian novels, and late-night sci-fi board game parties fool you. Organizations should be cautious when contemplating taking on data science projects that are not core to their business.
It is important to understand who we are. Over the past few years we have seen an increased desire for organizations to deploy in-house data scientists to projects into areas outside of their core competence. There is an allure here. Building new metadata, customizable intelligence like name, area, product, internally on a company’s highly valuable data can provide new intellectual property and possibly competitive advantage. With all this upside what’s stopping you?
Before tackling any DIY speech analytics data project, organizations should endeavor to know the full scope of the project. When it comes to complicated data projects like a speech analytics program, many organizations don’t fully realize the complexity until they are highly invested, and often are left footing a large bill with a suboptimal outcome.
Let’s look at why it’s attractive on the surface to undertake DIY speech analytics and the pitfalls companies we work with have encountered when they have tried.
Natural Language Processing (NLP) is cool
I am fortunate to work with a team of scientists in the cutting-edge field of AI, and very fortunate to do so for a leading company. I can tell you Conversational AI and NLP are some of the coolest and most avant garde AI research fields out there. I am talking self-driving car AI cool. CallMiner’s If we forget resources and cost for a moment, the advancements in NLP and commoditization of speech recognition transcribers, married with the power of current deep learning technologies, make this a lower cost of entry to a cutting-edge research field. As a data scientist, it is cost-efficient to try, easy to get prioritized internally, seemingly logical to a business, and cool AF. That’s a lot of wins.
So, what is the down side?
Recently, a client’s data scientist ran a recorded call with their significant other through a free online transcriber. The recognition accuracy was in the low 90%’s ergo the transcript was very clean. The client said their data scientist was sure he could build a better speech analytics system, at a lower cost than what we have been perfecting over the last 15 years.
We have deeply analyzed what it takes to arrive at parity with our impressive technology. Let’s walk through a few of the foundational hurdles of what it takes to build with something that basically works, which is still not close to where our software is today.
Problem 1: Transcription Speed and Accuracy
Don’t be fooled by one-to-one audio transcription rates of high-quality audio. Speech recognition software has come a long way in just the past few years (see Moore’s Law) and there are lots of options, even free ones, that produce acceptable transcription – but not at scale. Many technologies offer great results for one-for-one transcription: one call transcribed per CPU time, ergo a 5 minute call takes 5 minutes to process, upon completion the next one starts. There is a trade-off between speed and accuracy. Speech recognition software must deal with this, at scale, ergo high-processing speeds. CallMiner has algorithms that will contextualize with speed and endeavor to pick the next logical word, quickly. Your data scientist will need to deal with that.
Problem 2: Finding something relevant in the transcript
Once you find a good solution for transcription, the next step is to start finding the pieces of information in the transcript that can have a bearing on the business. You can build an algorithm to search for specific words, but this practice of “word spotting” does little more than show you singular instances of things. Data anecdotes. Our ambitious data scientist will learn very quickly two daunting truths, they are like natural laws of speech analytics.
Algorithms need to be built to not only spot a word or phrase, but also identify any of their aliases (ex: loan/lone/alone) and where they fall in the conversation (ex: before “payment”). Even at exceptionally high 95% accuracy with just a million words that is fifty thousand incorrect words that need to be dealt with.
The ability to build phrases together to create scoring also should be contemplated. As a basis for prediction, how relevant is the thing you found. A phrase by itself may not tell you much, but relevancy scores and counts of the same topic may be an indication of a significant change in customer behavior on that type of call.
Problem 3: Anomalies, quirks and tiny blackholes
So much of a conversation is not what you hear, not what makes sense, but what you don’t or doesn’t. Without a deep set of experiences (relevant data) finding the anomalies or missing things is nearly impossible. Let me share some examples that a data scientist who is new to this world needs to figure out. These are all real, and all sadly, very common among clients. Did you know that the candy “Tootsie Rolls”, among others, has a hotline, and that hotline has no required prompts, so it is effectively an endless loop. This is important if an agent who is not really working hard wants to take an unscheduled break. Just dial that number and sit there looking busy. That is something an organization may want to find in a speech analytics system. Or agents listening to phone rings for 5 minutes, or listening to 10 minutes of an answering machine, or an internal extension to listen to hold music for half an hour.
Even more diabolical is silence. Is silence good or bad? That depends, that tiny blackhole in an audio recording is speech analytics gold, highly important, and not trivial data science either.
Go/No Go time
As we all know anything “data and analytics” related will take dedicated time and effort by some very specialized resources, typically in high demand. Certainly, a big data project like speech analytics should not be expected to be completed as side project in any reasonable amount of time. Companies need to be willing to commit specialized FTE hours on an ongoing basis to ensure program success and should weigh the opportunity cost of such a venture.
Agent or employee engagement is a vital topic in call center management. Many contact centers are new to defining what employee engagement looks like, measuring, and figuring out how to tie employee performance to overall company goals. In a recent webinar nGuvu’s Pascal Leclerc on the top 10 employee engagement trends of 2019, we discussed an in-depth look at employee engagement, top trends to consider in 2019, and how to build employees in your contact center. Below are a few of our polls and audience questions answered!
How Do You Define Employee Engagement?
Employee engagement can be defined in several ways including agency satisfaction surveys, employee retention and employee performance to name a few. During the webinar, we polled attendees on how they define employee engagement. Employee performance was the main factor that businesses use to determine employee engagement with 35.64% of the votes.
Employee engagement is the level of psychological investment in the organization. This includes the buy-in, how strongly they feel about the organization they work. There is an associated cost with lack of employee engagement including:
These consequences for not having engaged employees can be detrimental to your organization if not acted on. These days employee engagement is a top of mind consideration for leaders across businesses. It is more important than ever to identify the value of the workforce and provide them with the tools they need to be successful. Simply retaining employees is no longer enough.
How Do You Currently Measure Your Employees Engagement?
Webinar participants were also invited to weigh in on how they measure employee engagement. Contact centers can review customer satisfaction rates, an annual employee survey, internal methodology, speech analytics, or employee turnover.
More than 45% of respondents shared that they only use annual surveys to measure engagement while another 20% use retention to measure it.
While the majority of the businesses define employee engagement by employee performance, only asking them about it at an annual employee survey is not valuable. Contact centers rely on data which makes it possible to measure employee performance and provide feedback daily.
When call centers use speech analytics software to automatically listen to, transcribe, capture, and quantify 100% of contacts versus only reviewing three to five percent of calls, they will be able to identify lack of engagement quickly. Agents require both constructive and positive feedback on how they are doing to push them to perform better.
How Can I Help Agents Learn and Develop?
A question that arose a few times in the webinar was a simple one: how can I help my agents learn and develop. Turn over rate is high for an agent and with training taking up to eight months, there is a big investment in agents. It’s very important to agents that their employer supports learning and development.
By analyzing 100% of customer interactions, you will take the guesswork out of identifying exactly where agents need help. And simply not picking only negative calls or a few from the dozens they do a day or week. This enables you to deliver tailored agent coaching rather than following generic training plans that may not be giving them the guidance they need. Supervisors can use the insight from analyzing all of their agent’s interactions with customers to create targeted training programs to ensure agents receive additional coaching to support an agent’s personal improvement objectives.
By giving every agent access to automated, daily scorecards, you can deliver fast and efficient performance feedback. This gives supervisors the opportunity to coach their agents efficiently. Perhaps more importantly, access to personal performance data (based on every interaction) also helps to create a culture of self-evaluation and improvement, as agents recognize where on the optimum customer path they could be improving their performance. For example, if the scorecard shows a need to improve empathy, the agent can focus on this during the next shift. Supervisors can also reinforce the desire to self-coach by using the daily scorecard to recognize the improvements the agent made on their previous shift.
PCI compliance call recording & transcription refers to the requirements set in the Payment Card Industry Data Security Standard (PCI DSS). PCI DSS is a set of strict regulations created to protect private financial information and prevent credit card fraud. To thwart would be fraudulent activity, credit card numbers (both the card number itself and the CV2 security number) must be hidden and protected by any entity which takes and stores the numbers in any way.
There are many organizations which, for one or more reasons, collect credit card numbers over the phone. These phone calls are often kept for many reasons, including:
Protection against liability
To ensure the quality of customer service
To train and evaluate call center staff
Perhaps the strongest reason companies record and/or transcribe calls is that it’s often required by government entities. However, in order to be compliant with the PCI DSS, the CV2 security number on the back of most credit cards must not be included in audio or transcribed conversations. The primary reason this number may not be included is that both the account number and the CV2 are required for would-be criminals to use a stolen card.
Methods for Ensuring PCI Call Recording & Transcription Compliance
Manual Filtration: Manually filtering recordings and transcripts is a process that takes place after calls take place. A representative of the company changes or covers the audio when a CV2 number has been mentioned. This method is obviously burdensome, but also unreliable in many cases.
Pause Recordings: A more effective strategy for PCI DSS compliance is to keep credit card information from ever being recorded in the first place. Before the conversation comes to a point where these details are said, the representative pauses the recording and resumes it once details have been entered. A potential drawback of manually pausing is that part of a conversation could be missed if the representative fails to resume recording.
With the advancements of computer technology, software solutions are available to automatically pause recordings when private information is shared during calls. Predictive algorithms listen for certain words and phrases in order to know exactly when to pause the call.
Redact: One of the most streamlined and sophisticated methods for maintaining PCI compliance is to use a solution like CallMiner’s Eureka Redact. Eureka Redact is triggered when the system identifies sensitive data (such as credit card numbers), and then replaces that data with the word “redacted” in text transcripts and a silence block in audio calls. By removing all sensitive data without sacrificing the context of conversations, companies can get the full benefits of customer engagement and speech analytics solutions to boost customer service and agent performance while simultaneously maintaining compliance.
Caller Entry: Some organizations opt to remove the need for screening, pausing or augmentation of recordings by allowing cardholders to input their own private information. By using the keypad on the phone, callers dial the numbers on cards, eliminating the potential for breach. There are still potential issues, including the different tones certain telephones produce for each number.
The Broader PCI DSS Focus
Call recordings and transcriptions are only a part of the requirements listed on the PCI DSS. Holistic policies and full compliance should be the aim of every organization under the authority of these guidelines. There are 12 individual requirements listed in the PCI DSS.
Some more notable of the 12 include:
Creating and maintaining a secure network
Restrict access to cardholder information only to those who “need to know”
Whenever data is digitally transferred on public networks, it is to be encrypted
Penalties for Non-Compliance
Transgressing the PCI DSS will likely mean fines, but how these fines are handled gets a bit tricky. Typically, it’s banks that are fined for non-compliance and fines range from $5,000 to $100,000 per month. However, according to PCIComplianceGuide.org, “The banks will most likely pass this fine along until it eventually hits the merchant.”
After fines have found their way to merchants, the banks often change their relationship with said merchant. Depending on the severity of the problem, the bank could terminate any relationship or raise fees. Any of these actions can be detrimental to businesses with non-compliance issues.
The Need to Implement or Improve PCI Call Recording & Transcription Compliance
According to one Verizon study from 2017, 4 out of 5 businesses are not payment compliant. Lack of compliance puts businesses at an incredible risk. The average cost of a data breach is $3.62 million dollars, but with proper measures these costs have been shown to reduce dramatically.
Compliance is as sensible as it is necessary. It’s vital to carefully review the standards required by all security regulations. And when choosing solutions for your call recording and transcription, ensure security is a priority. These steps will save potential fines, better protect customers and reduce the damage in the event of data loss.
Expert PCI Compliance Tips & Best Practices
Looking for expert advice and strategies for maintaining PCI compliance? Below, we’ve rounded up 17 tips and best practices for PCI compliance from industry and regulatory experts.
1.Look at the bigger PCI compliance picture. “The activities you’ll incorporate can vary depending on your PCI DSS scope, but some examples include scope validation, segmentation checks, bi-annual firewall reviews, active logging and monitoring, vulnerability scans, security awareness training, and policy and procedure updates.” – Brand Barney, The Secret to Smooth PCI Compliance, PCIComplianceGuide.org; Twitter: @ControlScan
2. Double-check that your entire network’s security system is adhering to the regulations. “It’s also critical to ensure an entire network system is compliant with PCI guidelines. This begins with an effective firewall and router, as well as internal processes that provide additional layers of protection. All traffic from unsafe networks and hosts should be restricted, and there should never be any direct access between any network component containing cardholder data and the Internet.” – Scott Kendrick, Vice President of Marketing at CallMiner, 10 Keys to PCI Compliance in the Contact Centre, Contact-Centres.com; Twitter: @contactcentres
3. Expand your call recording practices. “First, establish a plan and policy to record audio calls beyond simple client transactions. This should cover expanded regulatory expectations, and more importantly, best practices for audio recordings when business, products, and offers are discussed. Recording enough calls and call types helps avoid providing a guided path to malfeasance and conduct risk. This sets the expectation within your organization that there is compliance monitoring and there isn’t a loophole to avoid recording.” – Financial Services Compliance: Best Practices for Audio Recording Supervision, Theta Lake; Twitter: @thetalake
4. Ensure that your vendors are supportive and compliance-minded. “The best way to narrow down your search for PCI-compliant service providers is to check their PCI data security standards (PCI-DSS) compliance status. This method ensures that they have the internal security controls in place required by the PCI Data Security Standards Council (PCI-SSC). The PCI-DSS is a global standard that was adopted by all payment card brands to apply to service providers and is set by the PCI-SSC. To meet compliance, a service provider must have the following goals for their internal controls.
Creating and maintaining secure networks
Protect cardholder data when in storage, and during transmission through public networks by using encryption methods
Having a vulnerability management program to protect software programs, systems and applications
Applying strong access control measures to prevent unauthorized employee access
Monitor secure networks to track access to cardholder data and regularly test security systems
Develop and maintain an information security policy for all your employees
5. Ensure that you are operating under the correct understanding of PCI compliance for your contact center. “The impact of PCI DSS has been far-reaching, and its goal to minimize payment card data loss (malicious or otherwise) from merchant and service provider environments is becoming a reality. For all merchants and service providers, this requires appropriate measures to protect any systems that store, process and/or transmit cardholder data. This impacts call recording management and storage, and control of the agent/caller interface within the physical call-center space. The PCI SSC produced this Information Supplement to clarify the PCI DSS requirements on voice recordings, to provide some best practices, and to promote consistency among merchants, service providers and the assessor community.” – Information Supplement: Protecting Telephone-Based Payment Card Data, PCI Security Standards Council; Twitter: @PCISSC
6. Map data flow and practice transparency at every step of the payment process. “Requirement 3 of PCI-DSS states that data should only be stored in specific, known locations with limited access to protect credit card information. Organizations must therefore map their data flow and regularly conduct network scans to ensure credit card information has not been saved or forgotten in unpermitted locations by careless employees.” – Andrada Coos, 5 Best Practices for PCI DDS Compliance, Endpoint Protector Blog; Twitter: @cososys
7. Take the necessary steps to guarantee the security of all of your servers. “Even if credit card data passes through your self-hosted (i.e. non-SaaS) e-commerce platform, you are still on the hook for ensuring that any related servers you control (be it your database server, PoS system software, credit card processing terminal, utility server or internet application server) are sufficiently secure and compliant.” – Jon C. Marsella, Founder and CEO of Jasper, Everything You Need to Know About Achieving PCI Compliance, BigCommerce; Twitter: @Bigcommerce
8. Train agents thoroughly on everything compliance-related and integrate PCI best practices into their scripts. “Make sure that all call centre agents understand the rules and regulations specified in the PCI DSS policies for call centres. Provide remote agents with continuous training focused on PCI DSS compliance and measure their progress over time.” –Implementing Complying PCI DDS to Offshore Call Centres, Global Outsourcing; Twitter: @GlobalOutAu
9. Implement role-based security logins. “In any contact center environment, agent and supervisor desktops should have role-based log-ins to limit the number of staff exposed to sensitive data and ensure individual staff members only have access to what they need to do their job. A Contact Center World white paper on security and PCI compliance in cloud-based contact centers offers an example of how this might work: ‘A sales representative might be able to view customer details, but they may not be able to update or delete them. A team supervisor may be able to view the performance of the team that they are assigned to, but they (supervisor) should not be able to view the performance of other teams within the same Contact Center or project.’” –Scott Kendrick, Vice President of Marketing at CallMiner, 5 Keys to PCI Compliance in the Call Center, CallMiner; Twitter: @CallMiner
10. Meet all PCI DSS employee background check requirements. “The PCI DSS requires (via Requirement 12.7) that a background check be performed on any prospective employee who will have access to cardholder data or the cardholder data environment. Background checks are also recommended (but not required) for employees who only have access to one card number at a time when facilitating a transaction, such as store cashiers. Background checks can include verification of previous employment history, criminal record, credit history and reference checks. The PCI DSS does not specifically say you have to do all of these things, only that you ensure background checks are completed prior to hire and that you conduct the background checks ‘within the constraints of local laws.’” – Dwain Wright, What Does the PCI DSS Say About Employee Background Checks?, PCIComplianceGuide.org; Twitter: @ControlScan
11. Document all updates and protocol changes. “Once you have the needed documentation, it is important to keep it updated. Companies should document all changes to the security environment throughout the year. It may be helpful to schedule monthly time on your calendar to create updates based on agent and management feedback. This information will be very helpful during your annual PCI compliance review.” – Shelby Farris, Marketing Manager at Bright Pattern, PCI Compliance: What it is and How Call Centers Achieve Compliance, Customer Think; Twitter: @customerthink
13. Understand not only what data you must protect, but where it exists and through what channels it’s transmitted. “Most critically, you need to understand how your people and processes deal with credit card information. Not just at the 60,000 foot high level about what is supposed to happen, but what actually happens. You also need to understand what technologies are in play and what components see the data. A seemingly simple change such as from old fashioned analogue telephony to VoIP or from a fax to a fax server can have a huge impact on your compliance footprint. Lastly you need to understand the data itself. In a call center context, cardholder (and sensitive authorization) data include the primary account number (PAN), security validation codes, and PINs regardless of the form or media type. Digitized voice, voice recordings, recordings of IVR/DTMF tones, images, videos, text data, and hard copy all must be protected.” – Call Centers and PCI Compliance: Things You Need to Know, Control Gap; Twitter: @ControlGap
14. Narrow your PCI scope. “Looking at the matter internally, you will want to narrow that scope to the smallest footprint possible(realistically and in keeping with the PCI DSS guidance). The key to reducing scope is having fewer places that process the sensitive elements of the consumer’s information and fewer connections to external processes or technical environments. This simplifies your compliance efforts and lowers your “attack profile” from the perspective of your security teams. In many ways, this goes back to the basics of consumer privacy. Don’t collect the data if it isn’t necessary… and if you do, take care of it in the proper manner. This can be a bit of effort up front, both for the business and for the IT organization, but it will be worth it, not just for compliance and peace of mind, but because it also simplifies your operation in the process, producing fewer moving parts that could go awry throughout the course of daily business.” – Chris Conner, VP of US Customer Operations at Astute Solutions, Customer Data Security Part 2: What You Need to Know About PCI Compliance, Astute; Twitter: @astutesolutions
15. Give agents answers for real-life consequences for PCI non-compliance. “Since compliance is complex, invest in teaching your agents the rules (based on what your particular compliance issues may be). Your training program should include written standards for call agents, explaining handling ‘personal identifiable’ information (credit card numbers, social security numbers, birth dates, addresses, etc.). For example, if you take credit information on calls, it is against PCI-DSS standards to EVER store the CVV2 number. If you’re recording calls, you must programmatically or manually stop voice recording when the customer provides the CVV2.” –Best Practices for Call Recording in Call Centers, Ricochet360; Twitter: @speedtocontact
16. Give managers a system to police their agents. “Call centers have become the hub of service. Maintaining customer satisfaction is job one, yet customer satisfaction is not something easily measured. Most call centers create agent call center KPIs to assure that standard of behavior are met. Indicators are measured numerically and objectively – number of calls answered, minutes of customer hold time, one-time resolution ration, etc. These metrics can be measured by the phone systems or call center solutions – with or without recording the actual customer interaction.
As service has become more complicated, so have the ways in which we measure service. An often-used subjective measure of ‘quality of service’ is call scoring. Call scoring for quality assurance can work one of two ways:
Random Audit Live Call Scoring: A supervisor or service coach randomly audits live calls and..
Speech analytics has come a long way since its introduction. No longer is it constrained to the walls of traditional quality assurance.
Earlier this year, I sat down with Brian Cantor of Customer Contact Week, Marvie Wright of Qualfon and Chad Schott of HomeAdvisor to discuss how, when used correctly, your speech analytics strategy can use your organization’s objectives to transform legacy call centers into forward-looking value centers. While some behaviors become best practices for implementing an effective customer experience strategy, others can put your organization at risk. With the right technology, companies can see what’s working and which areas of the business need improvement.
If you’re not already capturing every customer experience from beginning to end, you’re missing out on adding business value by limiting yourself to a very small percentage of total interactions. But many organizations are just looking to say they “do speech analytics.”
When it comes to gathering insightful data, it’s not just set it and forget it. Your speech analytics tools are just tools unless you have the knowledge behind it. What you’re really looking for is the ‘why’ behind your scores, so you can take the steps necessary to improve them. That’s where our platform comes into play.
“CallMiner is like an internal analytics GPS. They tell you when you need to turn left, when you need to turn right, and where to take your business,” said Marvie Wright, director of leadership and sales training at Qualfon.
At the end of the day, customer analytics involves a lot more than gathering data—which is why you should be looking for a partner as opposed to a provider. See more about Marvie and her team’s success at Dialog Direct (now Qualfon).
Don’t: Follow the status quo when creating your objectives
There’s no universal objective when it comes to speech analytics. While everyone shares a commonality in that they’re looking to gather customer insights, each company has its own mission statement and unique goals. That’s why you need a platform that is both flexible but comprehensive, so that the user can be the acting force behind it.
It’s also important to remember that if you wanted it to, your technology could do a million things. While this opens the door to infinite opportunity, it also makes it easy for your organization to lose its way in the process. CallMiner helps identify individual, customized benchmarks tailored to the needs of your organization, and grows alongside your business.
Do: Educate beyond your business intelligence teams
One of the key elements to any successful long-term solution is internal education — which holds especially true for any customer experience platform. Real-time data and actionable insights can only do so much if all relevant parties are not onboard.
Getting adequate support for technology and initiatives requires strong communication across departments. Wright, for example, emphasized the importance of keeping the entire organization in the loop. “Everyone has to be on the same page, so the outcomes can stay as rapid as the technology,” she explained. She also noted that one of the key areas that customer analytics helped her organization was through improving onboarding using speed-to-readiness metrics—which wasn’t even included in the original strategy. Her goal now is to expand the technology throughout the entirety of the company
Don’t: Fall victim to tunnel vision
I spoke with Chad and Brian about a customer that came to us convinced their average handle times (AHTs) needed to be lower. Come to find out that, after benchmarking, their most successful calls resulting in the best sales results, least cancellations and highest compliance ratings, were 3.5 times longer. There have been many cases like these, where customers come in thinking they’re looking for something, just to discover they’ve been analyzing the wrong thing all along.
As hard is it may be—strategic developers need to break the self-affirmation cycle. Sometimes the data is going to show you that you’re wrong, but on the flipside, will show you what you should be doing instead.
Through speech analytics technology, you have the ability to uncover things that people normally aren’t thinking of, and then quantify the value to uncover new opportunities and create sustainable revenue. But in order to so, you have to think outside the box and be willing to accept that data, even when it doesn’t conform to your expectations.
Over the past few years, there’s been a huge shift in the industry’s willingness to even have the conversation around technology as a business intelligence asset—but it’s time to take it even further. Not only are we using speech analytics to capture 100 percent of our interactions, we’re looking to turn those interactions into actionable insights that will improve customer and employee experience and ultimately enhance business value.
To listen to the full conversations, visit the CCW Digital website.
Check out our AI experts thoughts on these 6 questions from the Contact Babel user community:
What are the steps we need to take to use AI in our contact center? Where would be the best place to start?
AI can be applied to many places in a call center. One of the first things is probably to start with speech recognition. Without the text transcripts, audio recording in the raw format is much harder to work with. Once we have the text transcript, many natural language processing tools can be used, including search and count of words, scoring of agent behavior, and live monitoring of agents to give suggestions. Prediction models can also be generated based on a specific purpose, such as first call resolution prediction. Speech recognition is essential in this process, there would not be any text analysis without it.
Is there anything that successful AI implementations / projects have in common? Any pitfalls to avoid?
AI comes in variety of forms. Whether it’s the traditional AI that include natural language processing, or the newer forms including statistical learning, people who are implementing the AI must have a good understanding of the data they are working with. Written words and transcripts of speech use the same words differently or may use different words entirely. The same algorithm used on both is going to generate different results. One of the major pitfalls is using readily available tools without understanding how AI works. Because the tools for building model is so easy to use these days, people may not understand the math behind it, and it could generate biased or dangerous models.
How do we measure the ROI of AI? Are there any quick wins we can use to show our senior management?
Start with a simple task. AI is basically a fancy computer program with statistics underneath. Both computer and statistics work well on a large scale. AI is much better doing a specific task, and not good at uncommon tasks that require frequent interpretations. Start with a task that improves the internal process, like faster search function. This will allow you to develop partners in other parts of the company and gather supports.
Solutions such as speech analytics and knowledge bases / case-based reasoning have been around for a long time. What’s so different about AI?
Speech analytics belong to the category of “Good Old-Fashioned AI” or symbolic AI. This kind of AI uses human knowledge to build rules that best replicate results, which are viewed favorable by humans. Statistical learning AI, which is commonly referred to as AI in the current media, uses statistical models to predict results by correlating previous observations with results. In the statistical learning process, AI generalize rules that may or may not make sense to humans. You can use these AI generated rules as features to make predictions. The outcome of these AI generates rule is outperforming symbolic AI in many areas.
How much initial and ongoing effort/resource will AI require? Do we need a dedicated AI professional to keep everything running?
Building models that make accurate predictions without bias requires constant human intervention. In the initial stage, a team consisting of a user experience designer, a data science, and a developer will be needed to frame the solution, build a model, and deploy the model respectively. The data scientist and developer will need to adjust the model from time to time, and make sure it functions as intended. Our world changes constantly, and they have to make sure the world did not change so much, so that the model no longer fit the problem anymore. There will be hardware requirements, but they are much easier to identify and acquire.
Does AI require replacement of any existing technology, or will it work alongside what we already have?
Initially, we would build AI to fit the existing technology and solve a specific problem. To make the AI more effective, some changes to the existing technology will need to be updated or revamped for the long term. A lot of the updates are going to be focused on accessing the data faster.
In 2012, CallMiner lead the way in the industry with the first version of a genuine automated performance feedback portal for contact centre agents, supervisors and coaches. Now, our latest addition to the CallMiner Eureka platform, Eureka Coach, continues CallMiner’s proud tradition of speech analytics leadership in the marketplace.
Eureka Coach enables contact centres to build an agent culture that underpins an excellent customer experience, improved compliance and reduced risk. It empowers managers and agents to focus on the importance of coaching and self-improvement. While Eureka Coach is the latest integrated iteration of our Performance Feedback portal, it is based on the proven notion that consistent, unbiased scoring and feedback provides the best way to ensure that agents and coaches are on the same page. Eureka Coach enables contact centres to:
Improve coaching effectiveness By objectively scoring each interaction, and summarising all interactions and scores, Eureka Coach enables coaches to target the key performance indicators where additional support can help drive agent improvement.
Drive positive culture change Role-based dashboards encourage a culture of optimisation. They also change coaching from something that supervisor ‘do to agents’, to something that happens because there is a mutual desire to improve performance from both agents and coaches.
Inspire and motivate higher achievement Because there is greater acceptance by the agent community (and coaches) of the trusted objectivity of the interaction scoring, Eureka Coach encourages agent self-improvement. Agents can see where they need to improve and where they can build on strengths. This complete picture on performance not only builds confidence but also pride in the positive outcomes they deliver for customers and the business.
We’re proud to share some of what our customers told Call Centre Helper that they love about our platform:
Our customers said they love Eureka Coach for the following reasons:
“The overall product design and the ease of using it. Once configured, it’s easy for even agents to navigate and improve themselves. The Coach function is amazing.”
“Accuracy and flexibility”
“Agent self-coaching ability”
“Configurable, easy to navigate and constantly challenging the status quo”
“Ease of coaching to agents within the tool. Dashboards are user-friendly and easily understood when onboarding new agents.”
“Easy to set up and use”
“Easy to use, plus absolutely incredible support the few times I’ve needed it.”
“Great customization and configurability”
“I feel like CallMiner is a true thought-leader in the speech analytics industry. The capabilities are endless with this tool.”
“Simple to use and gives you all the information.”
“The community surrounding the product.”
“The ease of the application and the detail it provides.”
Gamification is a fun and popular way to improve agent performance,
satisfaction, and effect the outcomes from those contacts with your customers.
Using analytics and gamification is an effective way to encourage successful behaviors
with the right incentives to measure, monitor, and promote the KPI’s vital to your
contact center’s and company’s success.
In a recent webinar with employee engagement and gamification experts nGuvu, we covered what gamification is, what it can be in regards to a formal platform, and what it can be from a strategy standpoint. Check out the webinar of 10 tips in 2019 or read more insights from the webinar below.
Symptoms of Lack of Agent
70% of employees are disengaged from work costing US businesses
300 billion each year according to a recent Gallup poll.
Symptoms of low engagement include:
Diminishing revenue recovery
High abandonment rate
Poor employee retention
Successful gamification programs requires understanding the
fundamental distinction between motivational triggers and using them in your
environment to achieve the desired result. Motivators vary depending on an
employee’s personality and generation. Millennials are different from
Generation X and Baby Boomers. Gamification has to be customized to fit
different types of employees based on intrinsic and extrinsic motivators.
Applications of Gamification Success
Defenders is the premier provider of ADT home security. Their focus on gamification is contest-based that shares rankings among call center teams identifying top agents, offers tangible rewards, while seeing what drives the metric outcomes they are looking for.
Contests became a simple way to drive metric outcomes that created employee engagement. While everybody participates, not everybody wins. Every contest includes five parts to be successful.
1. Start with the End in Mind
Understanding what business objective you want to drive. That can include metrics or a business behavior.
This includes when it should take place, how long it should last, and how to keep employees focused on a specific metric for a certain period of time.
3. Clearly Outline Rules
How to participate and how to win. Some contests include qualifying metrics, so there isn’t a decline in certain areas during the contest.
4. Consistent Communication
Explain the why to everybody that is participating. Helping everybody understand the importance to the business and at the agent level. It is also important to explain to stakeholders why the metric is important and how the contest helps to drive that. How will you communicate results? Scorecards, emails, etc.
5. Clear ROI for Participants and Leadership
What improvements will you see? Why does
it benefit the business? Why is it worth the time spent coordinating and
executing the contest?
Contests can be themed based on events occurring in the month or
focused on new launches within the business.
Defenders has documented the following improvements across their various gamification contests:
Improved net promoter score
Improvement in agent scorecards
Improved agent engagement
Agents embraced self-coaching tools
By measuring what matters and improving the experience, you ultimately are improving the business bottom line.
Through using speech analytics, you can measure behaviors and
assign a metric to it. It is not just about descripting, but are you following
the process you are looking for? Are you truly empathizing with the customer?
Saying “I understand” shows some empathy but saying “I am so sorry that
happened, I can’t imagine how that must feel” is the behavior of empathy. Using
interaction analytics to identify what does a behavior sound like allows us to
put that metric around it.
What happens if the characteristics or behavior don’t fit within a pool? How do you address that?
You can create a pool for every call. Encore Capital Group found a 10% gap and created a fourth pool for calls where the words were said but needed to be clearer. The absence of all four pools allows you to identify risks.
What happens when the contests are over? How do you sustain the behavior?
Typically, Defenders sees sustained results but not at the same
results as the contest. Overall, they do maintain a higher level than
pre-contest. It provides the opportunity to have conversations that you know
they can do it because you have already seen it.
Do you launch games with multiple departments at one time or are they primarily one department?
Launching contests simultaneously is possible if you have a
clear cut structure for establishing them.
We are well within the “Age of the Customer”. The first step toward competing successfully in this era is capturing the voice of the customer. Many organizations are sitting on a gold mine of customer intelligence which they have already captured – their contact center call recordings. Unfortunately, call recording wasn’t designed for the purpose of analytics and insight. The design of many recording platforms pre-dated the rise of AI-fueled speech analytics, which automatically transcribes and analyzes your call recordings. Call recording was initially designed for the purpose of storage and archiving, often to meet specific regulatory needs. As a result, storage efficiency was prioritized over recording quality – recordings are often highly compressed, degrading the audio quality. The agent and customer speaker tracks are commonly compressed into a single mono audio track.
Speech recognition accuracy is impacted in the same manner
as our own human understanding and comprehension when applied to call recording.
From a commonsense perspective, would you rather listen to a transistor radio
or a high-fidelity audio system? Speech recognizers share that same preference
– the better the quality the audio, the better the speech recognizer can
identify what is being said.
As humans, we experience the same challenges understanding
someone when there’s noise or distortion on the line, interference from
background noise, the signal is compressed, or the person is mumbling and not
articulating their words. I was once tasked to work with a client who was
having challenges with their speech analytics program. I received a handful of
call recordings to listen to – the audio quality was so poor, the agent and
customer conversation was for the most part unintelligible, even by a human. It
was no surprise they were struggling with their speech program!
There are several ways to avoid these issues including
effectively designed work environments, high-quality noise canceling head sets,
and coaching agents to speak at a reasonable pace and articulate their words.
But one of the most effective changes you can make is ensuring you are
capturing high quality audio in your recordings – the ideal format is
uncompressed PCM WAV files at 128 kbps or higher. The following chart compares
the impact on accuracy loss for various audio file formats and bit rates in
comparison to that ideal file format.
Image courtesy of CallMiner
This other figure shows a comparison of PCM Wav to MP3. MP3
on the right loses frequencies above 3khz, but speech recognizers (phonetic or
full transcription) require these frequencies to accurately differentiate
phonemes that make up the sounds in speech.
Image courtesy of CallMiner
Combining the two speaker channels – agent and customer –
into a single mono signal, does not necessarily have direct impact on the
accuracy of the recognition, except for periods of over-talk where both
speakers are speaking at the same time. However, conducting analysis on mono
call recordings does require more effort to extract insights. Analysts looking
to specifically measure agent vs. customer behaviors or activities in such
instances where only mono recordings are available, need to properly pattern
for the way an agent might express a behavior differently than a client.
A very rudimentary example of this could be a customer driven escalation “let me speak to your supervisor” vs. an agent mention “let me check with my manager”. This takes more time, thought and effort to accurately identify. Speech analytics still drives substantial business value when conducted on mono audio – in fact 46% of CallMiner’s customers have mono call recordings, while 41% have stereo and 13% have a mix of stereo and mono. This is likely a reflection of the general market in call recording. However, stereo recording is becoming more common with the rise of analytics and cloud contact center growth where the signal is not necessarily going through multiple switches to get to its final recording destination.
A final potential challenge with call recording systems of yesteryears is that some vendors don’t feel you have a right to access to your highly valuable voice of customer asset. The very conversations you have with your customers that you have paid to capture through your investment in call recording are held hostage for a hefty ransom by some vendors. Fees are charged to allow you to extract that audio for analytics or other purposes. In this age of the customer and the era of “big data” be sure to check your vendor contracts closely to ensure you own and have access to the data that you are capturing. Don’t be a data hostage!
High quality, stereo conversations can be captured
independently and in parallel to your existing recording systems if none of the
above options are feasible, or especially if you are stuck with a vendor who is
holding your voice of customer data hostage. This is often referred to as Call
Capture or Recording for Analytics. Such a solution captures the audio in a
manner that supports accurate speech recognition and becomes the foundation for
a highly successful speech analytics program with little to no impact to your
So what should you do if you are already invested in a call recording system that you cannot replace immediately? Not to worry, you do have options. Check to see if your recording solution has settings to allow for capturing higher quality recordings, and/or the ability to retain the agent and customer speaker tracks in separate channels. In some case this interim format can be made available for your extraction even if a lower quality file is ultimately stored for archiving purposes. Explore using software to separate your mono recordings into separate speaker tracks using voice biometrics. Software-based speaker separation or “diarization” can be a great second-best option if you can’t get native stereo audio. This software listens to the signaland identifies who the agent is and who the caller is by discerning voice tones. While it’s not 100% accurate, our customers have found that there are definite downstream gains in analytical productivity that justify the investment and any misses on accuracy.
Gain control of your call recording assets
Capture superior quality audio from you customer
Identify customer and agent interaction insight
from every call to your contact center
If you are an existing CallMiner Eureka user, exploring
speech analytics, or concerned about access to high quality recordings of your
customer conversations contact CallMiner today to discuss how Eureka Capture
can help you:
Call center regulations are complex. The Fair Debt Collection Practices Act (FDCPA), for instance, requires debt collectors to disclose the purpose of their written or oral communications at the start of every contact (the mini-Miranda). Additionally, the FDCPA has strict requirements that stipulate when, where, and with whom a debt collector may communicate with consumers. All of these requirements aim to protect consumers from unfair debt collection practices. As the debt collection industry continues to grow, more debt collection agencies turn to interaction analytics to improve agent performance while also mitigating compliance risks.
But the debt collection industry isn’t the only industry facing regulatory compliance concerns. PCI DSS, the Payment Card Industry Data Security Standard, applies to all companies that store sensitive cardholder information and aims to protect consumers from the misuse of personal information shared during cash, credit, and debit transactions. For call centers, PCI DSS compliance means ensuring that appropriate encryption and other network security measures are in place, as well as redacting sensitive personal details in recordings. Solutions like CallMiner Redact use speech analytics technology to automatically mute call recording when sensitive information like account numbers, security codes, and other sensitive information is spoken, ensuring that such sensitive payment information is not recorded at all.
There are myriad other regulations that apply to call centers as well, from the TCPA (Telephone Consumer Protection Act) to HIPAA (the Health Insurance Portability and Accountability Act of 1996) to myriad state-specific regulations. Still, call center regulations aren’t perfect, and there’s plenty of room for improvement. To find out what today’s consumers, businesses, and call centers would improve about call center regulations, we reached out to a panel of call center pros and business leaders and asked them to answer this question:
“If you could wave a magic wand to improve one aspect of call center regulations, what would it be?”
Panel of Call Center Pros & Business Leaders say about what aspects of call center regulations they’d like to improve.
Joe Pores @call4health
Joe Pores is the President and CEO of Call 4 Health and this year’s President’s Award recipient from ATSI (Association of Tele-services International).
“It’s time to remove the burdensome and unnecessary HIPAA regulations for…”
TAS (telephone answering service) companies who do not deal directly with medical information. Typical TAS companies serve strictly as an overnight messaging service, only collecting contact information from the caller for processing the next business day. Yet, they are required by law to be as HIPAA compliant as a major hospital system, costing these small businesses tens of thousands of dollars in coverage that is essentially unnecessary.
Congress should review the regulations with common sense in mind, make compliance equitable and fair based on the kind of information being processed, and pass a de minimis (carve out) exemptions for these small TAS businesses.
Privacy is absolutely critical. But holding a small TAS to the same HIPAA standards as Call 4 Health is inequitable and unfair, and ought to be reviewed and acted upon accordingly by regulators.
Joe Laskowski is the Managing Partner and Chief Marketing Officer at Higher Ed Growth and LeadsCouncil board member. Higher Ed Growth (HEG) is a full-service marketing agency specializing in post-secondary education.
“Adhering to regulations is anintegral part of all call center activities…”
And the Telephone Consumer Protection Act (TCPA) certainly outlines some of the most important requirements. From reassigned number liability to revocation of consent, the TCPA continues to be re-examined in the courts. The present-day rulings shape the environment in which call centers can engage with leads, and it is important for call centers to stay on top of changes.
One pain point for call centers in particular? The variability in TCPA consents. Many clients require specific TCPA statements for their brand, which is hard to scale and automate. It would be more effective for centers to have one client-approved TCPA that can dynamically integrate brand names. It is a much more seamless process for agents and reduces the risk of TCPA statements being missed or misread.
Pam McWilliams is the Senior Director of Customer Experience at Ancient Nutrition. She is a 30-year veteran in direct to consumer marketing and customer retention. She is a proven leader in all aspects of business development and marketing, taking campaigns successfully from inception to completion.
“If I had a magic wand to improve one aspect of call center regulations…”
It would be to have one federal law to follow, rather than so many varying state-by-state laws, for making outbound business calls to existing customers.
Although technology allows us to use programming to sort customer lists, it can be burdensome to keep up with all the individual laws. I understand the need to protect consumers who are not existing customers. However, when speaking to your active customer base with special offers, in my opinion it should be easier for a business to manage.
Outbound calling is an excellent tool for a business and for the consumer. For the business, it allows a personal connection with customers, which improves customer retention, increases sales, and provides the consumer the opportunity to ask questions about products, programs, and services. For example, sometimes we find a customer is not happy with their purchase, so this call gives us the opportunity to do what it takes to satisfy a customer. I am “old school,” so using pre-recorded offers is not my style. However, being able to use a dialing system really makes for efficient work flow for my business and we can connect our customers with a live person.
If a business takes all the proper steps to execute an outbound calling campaign by following the laws and keeping an internal DNC list, the fear of making a mistake due to a certain state’s calling rules can be why they hesitate to use this very productive form of marketing to existing customers.
With 35 years of experience, Margie Brickner is a trusted advisor in the collections industry. Over the course of her career she has developed the necessary skills, experience, and knowledge to run a successful collection operation. She is the President and Chief Executive Officer of Reliant Capital Solutions.
“We are long overdue for a comprehensive review and modernization of…”
The Fair Debt Collection Practices Act (FDCPA) and the Telephone Consumer Protection Act (TCPA). The FDCPA was approved in 1977 and the TCPA was approved in 1991. Neither act has been amended to materially recognize current consumer practices. For instance, the TCPA specifies many requirements for fax machines and restricts text messages received by cell phones but does not recognize the reality that most consumers use a mobile phone as their primary point of contact. These laws need to be amended to better balance consumer privacy with legitimate business communication.
“One thing I would change about call center regulations is…”
The number of times someone can call a specific number over a particular time frame. Let’s say you can’t call the same number (business or person) from a call center more than 10 times in 1 year. Right now, I get the same “help with your Google listing” or “do you need health insurance” call every 10-14 days.
I get that you have to make calls to do business and make money. I have to do the same in my own company. However, there is a limit. There might need to be stipulations on this rule, like if you can’t call more than 10 times per year per live answer. So, if a recipient doesn’t answer the phone 10 times in a row, you should probably not call them 11, 15, or 20 times.
Another change I would make is if you are offering a product or service in multiple states, you should be required to call from an 800 number and not a local area code. The recipients of these calls would know more than likely that if an 800 number popped up, it is a call center or automated voicemail call. They can then choose to answer or not. Tricking people into answering a call by using a local area code might get you a few more conversions but really makes people angry. If you operate only in one state, you can still use a local number, but anything wider than that and you need to present yourself as a foreign caller/company.
“Companies should save examples of their best and worst calls…”
The benefit of doing this is that it gives you a fantastic training guide for new starters in call centers, helping them to learn how to handle a wide range of situations when dealing with calls. This ensures they have a good groundsheet for their own calls, as well as examples of how they can continually improve and grow.
Analyzing these calls means you can find common language or signals within the calls which trigger positive reactions from the callers. In turn, this helps you to tailor your approach to build great rapport with as many customers as possible.
Regulations concerning strict liability against the sellers when the call centers violate the DNC list. The most impactful measure would be to protect the FCC’s imposition of strict liability of sellers in many situations rather than employing archaic agency principals, which typically allow sellers to easily escape accountability.
Sellers should be liable unless they’ve regularly monitored the call campaigns, materials, TCPA compliance (e.g., scrubs for cell phones and DNC registry), etc. In other words, the Safe Harbor regulations should be revised.
Taking such measures would help reduce pressure on sellers and call centers to engage in a race to the bottom which, if continued to be effectively left unchecked, is likely to lead to stricter statutory mandates.
Osiris Parikh is a consultant for Summit Mindfulness. He is a certified inbound sales professional and SEO strategist. He also holds educational technology certifications from Apple, Microsoft and Common Sense Media.
“In too many cases, I have seen call centers brush aside the importance of caller forecasting…”
This negligence of data leads to under or over-staffing, which will overload employees as well as cause a longer wait time for customers, which negatively impacts their experience. These problems not only affect an organization’s image, but it also leads to a depletion of profits; using too much time to resolve customer issues. By leveraging caller forecasting, call centers will have a better understanding of when customers call, and be prepared to be staffed appropriately to handle customer requests. Although it may not seem important, caller forecasting is the backbone of an effective call center.
Mandeep Kwatra is a digital customer experience design thinking evangelist and transformation professional with 19+ years of experience in customer service, call center, digital solutions, automation, and business transformation.
“The two methods by which an aspect of unsolicited/telemarketing call regulations could be improved…”
1. Real-time DNC update: We all get unsolicited calls at times about a promotional plan, a vacation deal, or credit card. The telephony dialer software solutions should develop an API to connect to the DNC registries maintained by the enterprise and the government body, and with the help of AI a number should be checked before it’s dialed out (in case it has missed the initial data cleansing). This will ensure that the customers don’t get unnecessary calls and help create brand credibility between the customer and the brand.
This should also apply to messaging marketing blasts. The Telecom regulation in call centers needs to cover beyond voice and SMS. It now needs to cover areas like Apple business messaging, WhatsApp, and Facebook messenger as they all hold private access to a customer’s life.
2. Second is the use of data and analytics in the telemarketing programs by the call centers. Most of the outbound small contact centers don’t, and maybe won’t, do it. But this needs to be regulated as well. If your brand has called a customer and the customer has disconnected the call on two occasions in less than 10 seconds of the call, the intent should be recorded as the customer does not want promotional calls and should be moved away from the list.
These will not only help customers but also help companies in putting their money where the mouth is and targeting campaigns to people who want these promotional calls and provide a better ROI with a spend on a controlled audience group.
Travis Ogden is the contact experience agent at The Zebra. With over 5 years in the sales/customer experience, Travis has seen (and heard) it all. Communication and service comes naturally, while the art of smoothing things over is a talent earned from experience.
“There needs to be more education in call centers…”
Customers are often given false or misleading information. Sometimes maliciously, but mostly because the correct information is not available. Especially in my last two jobs, it wasn’t uncommon to put people on hold to have a question answered only to receive shoulder shrugs, meaning there was no real answer to give the customer — either because the information they had received was false or us as the agents didn’t have the information on hand.
One of my previous employers was a TV provider that sold a Sports Package for about $15 to hopeful baseball fans looking to see every game. In reality, the “Sports Package” only unlocks the channel of the broadcast, but the actual game is blacked out unless they buy the far-more-expensive baseball-specific package. I got those calls ALL THE TIME. It’s a difficult conversation. I also dealt with angry customers confused about promotions, like free HBO auto-renewing and charging an account if not removed by the customer, when they were told it would automatically roll off.
The company didn’t want to credit anything so it would turn into a Supervisor Call. If they credit, great, if not, the customer wants to cancel and then Retention will just credit it for them anyway. If the customer got the correct information at first contact, that saves three additional calls and we don’t have to credit accounts.
It’s far more difficult to convince a customer the information you’re providing is accurate if they’ve already been told something different.
Kartik Prajapati is a self-motivated mechanical engineer with too many innovative ideas and always ready to face challenges.
“If I could wave a magic wand, I would like to improve the point to point solution to the customer…”
Sometimes, you have a minor, simple problem, and the call center takes you through so many processes to solve that problem. When you solve that problem, you discover that it wasted a lot of time behind that solution. As a result, you might never call customer care again, even if you really had a problem.
Bryan M. Waring is a composer/songwriter from the Nashville area, as well as the owner of his own freelance music production business, the Vintrine Of Bryan, Music COLL.
“If I could wave a magic wand to improve one aspect of call center regulations…”
It would be to make sure that I talk to the least number of people as possible. While most people (and presumably everyone) would agree that the wait while put on hold with awful “elevator music” is the worst, I would argue that it wouldn’t be as bad so long as the person did their job correctly and sent you directly to the phone of a person that can fix the query you have.
There have been a lot of instances where one call specialist transfers you over to another one, who then sends you to a new one, and so on, and so on… to the point it becomes a wild goose chase. Honestly, it should be “one-and-done,” which would be possible by them being knowledgeable of who will immediately fix the problem, and transferring me over to their line.
Riley Panko is a Senior Content Developer and Marketer at Clutch, a Washington, D.C.-based research, ratings, and reviews platform for B2B services. She conducts relevant research that aims to help consumers enhance their business and select the services and software best-suited to their needs.
“My magic wand would involve technology already being implemented…”
The STIR/SHAKEN initiatives that hope to validate trustworthy phone calls and combat malicious robocalls.
Clutch recently published a survey that found that 52% of people receive robocalls daily. A subsequent report revealed that 67% of people are unlikely to pick up a phone call from a number they do not recognize – creating issues for legitimate outbound phone outreach.
The FCC is working to implement a combination of the “Secure Telephone Identity Revisited” (STIR) standard and the “Signature-based Handling of Asserted information using toKENs” (SHAKEN) standard. Together, this technology will actively validate legitimate phone numbers by checking for the presence of a certificate, distributed by a trusted policy administrator. Past efforts to fight robocalls have involved retroactive, passive approaches – the Do Not Call list, for example, only works by going back and punishing robocallers who have already pestered thousands, if not millions, of people (and it doesn’t even work that well at that).
Customer interactions don’t happen in a vacuum; your customers interact with your company through myriad channels and at many different stages throughout the buyer’s journey. While analytics for single-touchpoint, single-channel interactions provide valuable insights into the effectiveness of your messaging at that juncture, they fall short of painting the full picture.
Enter customer journey analytics: a solution that eliminates data silos and combines otherwise segmented data to empower marketers to improve the customer experience throughout the entire customer journey, from end to end. Here’s what you need to know about customer journey analytics, its benefits, and how it works.
Definition of Customer Journey Analytics
Customer journey analytics is not the same as customer journey mapping. While customer journey mapping is the process of creating a visual map or representation of the touchpoints throughout the buyer’s journey, customer data analytics connects data from those touchpoints across all channels over time. That said, customer journey mapping is a valuable precursor to customer journey analytics.
Customer journey analytics typically refers to software that enables companies to manage the customer experience across all channels and touchpoints. According to G2 Crowd, customer journey analytics software “tracks, weaves together, and analyzes customer interactions across all channels so that businesses can react in real time and execute behavior-driven strategies.”
How Customer Journey Analytics Works
Customer journey analytics solutions are used to track and monitor customer behavior across multiple channels, from the first introduction to a brand or company throughout the entire relationship. Because the customer journey doesn’t end with the purchase, customer analytics solutions go past the point of purchase to monitor and analyze behavior through customer service interactions and beyond.
One hallmark of customer journey analytics is that it combines both quantitative and qualitative data. It allows companies to identify the customer journeys that have the biggest impact on specific business goals – such as increasing revenue or reducing customer churn – and making data-driven decisions designed to influence those outcomes. For instance, a company might identify a key set of touchpoints the majority of leads visit immediately prior to making a purchase, and then leverage this insight to better optimize interactions at those touchpoints to increase the percentage of leads that convert to customers. Alternatively, marketers could optimize the path to purchase by driving more leads to those key touchpoints.
Benefits of Customer Journey Analytics
By combining data about customer behavior with marketing metrics, companies gain a better understanding of customer needs and wants, as well as actionable insights that can inform decision-making.
What’s more, customer journey analytics enables companies to better forecast and predict customer behavior based on data gained through historical interactions and similar messaging at various touchpoints.
Customer journey analytics helps companies answer questions such as:
What’s the best time to engage a particular customer?
What channels are best for engaging with a certain customer segment – or even individual customer?
Which types of customers (personas) are most likely to take a given path to purchase?
Which channels or touchpoints are customers most likely to result in a purchase?
Which channels or touchpoints do customers visit most often before churning?
Armed with answers to these and other important questions, companies can make data-driven decisions to directly influence outcomes, such as intervening with targeted customer service efforts when a customer is following a likely path to churn.
Best Practices for Customer Journey Analytics
To get the most from customer journey analytics, follow these best practices.
Start with a customer journey map. If you don’t know what touchpoints your customers interact with, how can you be sure you’re getting data from the crucial stages throughout the buyer’s journey? Every touchpoint and interaction customers have with your business influence decisions.
Listen to your customers. Don’t ignore qualitative data, and don’t choose a customer journey analytics solution that deals only with quantitative data. Otherwise, you’ll be missing an important piece of the puzzle.
Use customer journey analytics to create personalized experiences at scale. While customer journey analytics can provide insight into the types of customers more likely to take a particular path to purchase – or which types of customers are most likely to churn after a negative customer service interaction – the real power of customer journey analytics lies in the ability to create one-of-a-kind experiences catered to every individual and maximize customer lifetime value.
Choose a customer journey analytics solution that learns over time. A customer journey analytics solution that leverages AI and machine learning becomes more valuable over time, as historical data informs forecasts to better predict which customers are most likely to take specific actions next.
Today’s customer journeys cross multiple channels and involve more touchpoints than ever before. Ordinary analytics solutions provide valuable insights, but this data exists in silos. By combining your data across channels over time with customer journey analytics, you’ll get a more complete picture of your customers to better predict and influence outcomes.
Are you using customer journey analytics to break down data silos? What benefits will your company gain from customer journey analytics?