Don’t Make These Mistakes When Buying Speech Analytics Software

Speech analytics software is a major and important investment for the contact center. Your speech analytics software should help with compliance and customer service while getting you the highest ROI possible. Avoid these mistakes when searching for new speech analytics software.

1. Assuming speech analytics will do everything for you.

Speech analytics software isn’t a set-it-and-forget-it solution, no matter how smart the technology may be. The software gathers data that you then have to review, make sense of and act on in order to improve your contact center. Only then is it truly powerful; otherwise, it’s simply a data collector.

2. Not taking advantage of the software’s potential.

Speech analytics software has a number of standard benefits, like agent training and quality assurance. When you purchase modern software, though, you have access to a host of other features you may not even know are there. New speech analytics software may include escalation language and objective compliance, for example.

3. Choosing software with poor recording quality.

To truly reap the benefits of speech analytics software, it has to be able to record clearly and transcribe accurately. If it can’t, you won’t get a dependable analytics report. Remember, you can’t improve audio quality after a call has been recorded.

4. Purchasing software for executives who don’t listen to calls.

Software brands know how to dazzle customers to get more sales. However, if contact center management isn’t currently listening to and analyzing calls, this may not change even after pricey software is purchased. It’s better to get in the habit of analyzing calls so that you know the software will actually be used (and also so you’ll have a clearer view of your needs).

5. Relying on software that doesn’t account for conversational language.

Your agents have to say certain things on each call, like “thank you” when signing off. Your speech analytics software has to detect that these keywords are mentioned in each conversation. However, if your software only detects exact words instead of conversational language, a version of “thank you” will go ignored, and the agent could get marked for not following procedure, even if they did.

In Conclusion

When buying software, identify your contact center needs, then find a solution that checks those boxes. Make sure you’re learning from your analytics, too, instead of just letting it auto-run in the background.

 

3 Contact Center Metrics Improved by Predictive Analytics

Predictive analytics predict future events by combining various techniques that analyze historical and current patterns. Predictive voice analytics can have a major positive affect on integral contact center metrics, including customer retention, follow-up call success and quality assurance.

Customer Retention

One of the customer service industry’s main goals is customer retention, and experts believe that it costs more to acquire a brand new customer than to keep an existing customer. Predictive voice analytics, which analyze the customer’s voice during customer-agent interactions, can determine if the customer is at high risk for ending their relationship with the company altogether. It can then inform the agent that they need to put more focus on retaining the customer. On the flip side, predictive voice analytics can also tell which agents aren’t doing enough to keep the customer coming back. This is more effective than random checking for quality assurance, which can take a long time to identify poor-performing agents.

Follow-up Call Success

Often, the first contact with a customer isn’t the one that has a positive outcome (i.e. a sale); it’s the follow-up call that proves to be more advantageous. However, it’s difficult to know which customers are a priority for follow-up contact. Instead of leaving it up to your agents to determine which customers are worth a follow-up call, predictive analytics can analyze past interactions and study voice features to determine if the customer’s tone and behavior predicts a favorable outcome during the next interaction (like making a payment or finalizing a sale). Predictive analytics can create a ranked list of customers, organized by their likelihood to say “yes.”

Quality Assurance

Predictive analytics are a richer way of assessing quality assurance than traditional methods. Routine QA testing often ignores customer patterns, and it is also unable to learn in real-time. Predictive analytics, however, can analyze all types of data, both structured and unstructured, to give a well-rounded view of agent behavior and how it impacts the customer. All customer-agent communication is assessed in-the-moment, allowing the contact center to get an accurate view of agent performance immediately instead of having to wait several weeks.

Contact centers can’t just gather metrics to assess their current performance and then call it a day. They must also use what they’ve learned from the past to create goals for the future. Predictive analytics can help shape those goals realistically.

 

 

5 Contact Center Trends to Watch

Contact centers have a lot of contradictory goals to juggle: focusing on both employee and customer happiness; modernizing while still utilizing helpful legacy systems; and upholding security while being open-minded enough to evolve. Contact centers are almost always in some sort of transitional phrase, with late-2017 being no different. Here are five trends you should either be familiar with or keep an eye on moving forward.

1. Omni-channel, not multi-channel, service.

Some contact centers mistakenly think that offering multi-channel service means they’re immediately able to deliver omni-channel support, but the two are quite different. Omni-channel services takes those multiple channels and seamlessly integrates them. Agent-customer interactions can be switched to a different channel mid-communication without losing any relevant data.

2. New digital channels.

Customers want convenience, which means being able to interact with customer support when they’re on-the-go. Emerging digital channels have to be adopted by contact centers, including mobile apps and web chat. These channels must be adaptable and easy to use, too, and they have to make it simple for customers to troubleshoot on their own and, when needed, get in touch with a live support agent.

3. Additional performance metrics.

Most contact centers have strategies in place to measure voice and call quality, but since digital channels are still relatively new, measuring them isn’t as commonplace. Understanding how agents perform on digital channels, including mobile, live chat and social media, can help to increase agent productivity and improve the customer experience.

4. Dependence on the cloud.

Though many contact centers have switched over to the cloud, others are still relying on their antiquated legacy systems. According to Customer Think, reliance on the cloud is about to increase dramatically, particularly over the next four years. More contact centers will move to the cloud, allowing them to scale globally, improve their data security and increase their efficiency.

5. Two-way conversations on social media.

The ways customers want to connect with brands on social media has changed – they now want to engage in a back-and-forth conversation with support instead of just observing the content a brand posts. Contact centers will need to train agents in how to chat with customers on social media platforms, both publicly (like on a Twitter thread) and privately (like on Facebook Messenger).

 

5 Tips for Root Cause Analysis in the Contact Center

The best way to solve a problem is to dig deep and find out where it started in the first place. Often, what you see of a problem is a symptom, not the cause. Here are five steps you can take to improve your contact center’s root cause analysis.

1. Consider acoustic issues.

Root-cause analysis should take acoustic factors into account. For example, if the call has long periods of silence, this could point to a problem with the system. If the contact center agent can’t access data quickly enough or if there are problems with IVR, a slow system may be the problem.

2. Flag conversations that are abnormally long.

Speech analytics will let you sort through calls based on parameters like duration and repeated calls. You can also find calls where specific keywords are mentioned, like those that are normally associated with a complaint. This will let you know which calls need the most attention.

3. Monitor data in real time.

Accessing real time data can help you spot and stop issues early. If a new sales or marketing strategy launches and then phone calls start coming in within an hour or two, you’ll know that there’s a problem with the launch that must be fixed. Real time data lets you identify trends as they emerge, giving you the opportunity to stop a problem in its tracks.

4. Sort problems into categories.

As you start to uncover the main problems customers are having, you can segment them into categories, such as product defects, customer education and marketing communication. Then, you can meet with specific teams to come up with targeted strategies to solve the problems.

5. Understand the context of the situation.

Relying on word count frequency isn’t enough – the terms and phrases that are being used have to be understood contextually, too. Knowing the context of a problem instead of just the hard data will allow you to pinpoint the situation that caused or contributed to it.

Knowing the average number of complaints your contact center receives on a weekly basis is just a start. You have to figure out the root cause of the complaints in order to effectively tackle them and prevent them in the future. Root cause analysis is a way to solve prominent issues instead of merely putting a Band Aid on them.

How to Motivate Contact Center Agents

There are several reasons to motivate contact center agents: hiring new staff can get expensive; training new hires means there’s lag time between when they’re hired and when they can start working; and company morale can decrease if there’s a high rate of turnover. Here are 5 ways to motivate contact center agents.

1. Provide agents with the necessary tools for the job.

All of the tools your agents use, from software to hardware, should work flawlessly. Faulty technology makes it impossible for agents to be efficient. One necessary type of tool are those that reduce customer frustration. Agents can get frazzled after speaking with one angry customer after the other. Software that allows for queue callback or voicemail can make customers happy, which in turn delivers agents fewer frustrating inquiries.

2. Setup seamless automation.

Quality contact center software will automate manual tasks so that agents don’t have to perform them with every single call or chat. Data should also be synced across all customer service tools. When their workload is streamlined, agents have more time and energy to handle more pressing issues.

3. Help agents hone their specialties.

Instead of having all of your agents trained in every area, figure out the strengths of your individual agents and help them specialize. Some agents may excel at handling agitated customers while others will have in-depth knowledge of your products. When you have agents who are experts in certain areas, they’ll be able to answer queries and solve problems more quickly than if they only had limited knowledge of the niche.

4. Open the lines of communication.

Your contact center agents are the closest people to your customers. It’s important that your agents know they can speak with you openly. Not only will you hear great ideas you haven’t thought of before, but agents who feel valued and needed are more likely to perform well in their job.

5. Use analytics to acknowledge excellence.

With call center reporting, you can see how agents are performing. When you find an agent who spends a short time on calls and has a high FCR rate, for example, you can reward them for their performance. You can also see which agents have positive customer reviews and reward them accordingly.

When your agents are motivated and happy, they’re better able to deliver the sort of customer experience you expect.

4 Trends that Improve the Customer Experience

When customer service teams want to differentiate themselves from the rest, they focus on improving and optimizing the customer experience. Companies are more than willing to go above and beyond for the sake of meeting and exceeding customer expectations. Here are four trends that will help distinguish your contact center.

Relying on Artificial Intelligence

Artificial intelligence (AI) is everywhere, from video games to the automobile industry. Customer service has been impacted by the increase in AI, too. This technology can be used to chat with customers about easy-to-solve issues, which frees up live agents for more difficult and complex matters. Automation with AI can reduce customer wait time, interact with customers and collect important data for the contact center to later analyze.

Implementing an Omnichannel Strategy

One major gripe that customers have is repeating themselves to various customer support agents in order to get an answer or have a problem solved. Channel integration isn’t the same as omnichannel service. Today’s companies can’t just respond to a customer, they have to know as much as possible about the customer and their problem beforehand in order to provide customized, relevant support. Customer service requires empathy and a human touch in order to connect meaningfully to the customer.

Analyzing Big Data

While much of the customer experience is about interaction and communication, big data still has a pertinent place in understanding customer behavior. Big data can actually help the contact center connect on a more personal level with customers. There’s so much information that can be tracked now, from customer behavior at every point of the journey to customer preferences regarding any number of attributes. Data helps customer support do things like figure out what a customer is going to want before they even ask for it and determine the best way to reach a customer on the channel of their choice.

Providing Real-Time Communication

Using things like AI, which can automate several processes, and ominchannel strategies, which can cut down on the length of time it takes to solve a problem, gives customer support agents the extra time to handle some queries personally. Real-time communication, specifically via mobile and social media, is in demand, especially by younger generations who are used to communicating in these ways. Being able to provide immediate support improves the customer experience and builds trust in customers.

4 Voice of the Customer Tools for Collecting Feedback

Analytics often track what a customer does, but voice of the customer tools figure out why someone performs an action. Several voice of the customer tools can be used to collect feedback. The feedback tool you choose depends on your goal.

1. Community Forums

Customers can discuss their experiences with one another in forums. These are great places to find out what customers need and which needs aren’t being met. They’re hubs for suggestions and ideas that a brand can use to guide everything from product development to customer support practices.

2. Visual Feedback

Brands that have recently launched a new website or mobile app can benefit from visual feedback tools. Elements on a page will have the option to provide feedback. The customer can make a note about what they think about a specific element and then a screenshot will be sent to the appropriate department or agent. The customer uses his or her own words to describe a problem, which helps brands figure out which parts of a page or app are faulty or unclear.

3. E-shop Reviews

E-shop surveys are auto-emailed to customers after they purchase or receive a product. A short assessment survey asks the customer to rate their experience or the product on a scale of one to five. There’s also a section where customers can write in an account of their experience. The benefits of this type of feedback are twofold. First, the brand learns about the customer’s experience and can opt to reach out to the customer if they submit low scores or describe a problem. Second, if the star ratings are published on a review site, other shoppers will be influenced by them, and a brand with high ratings will attract more customers.

4. Speech Analytics

Speech analytics delve deep into a recording to uncover intelligence from customer-agent conversations. Advanced software digs through dialogue to isolate specific phrases and words. Results can be organized and then compared to reason codes (why customers contacted support) as well as trends to determine recurring problems.

Voice of the customer feedback tools help contact centers to determine what people do and do not like about a brand. By pinpointing why someone may choose, stay with or leave a brand, the entire customer journey can be updated and adapted to meet specific customer needs.

 

How Speech Analytics Affect the Outcome of Calls

By the time a customer has contacted a live agent, they’ve probably tried to troubleshoot the problem on their own with self-service tools. When they’ve reached the point of wanting to speak with someone, they’re already part of the way through their customer journey. Real-time speech analytics take into account customer history so they can pick up where they left off instead of starting from the beginning.

Real-time speech analytics help agents determine the right thing to say to a customer in the moment in a variety of situations. On top of making sure the customer is directed to the correct agent or department, this technology also gives agents the current, relevant information they need to solve the customer’s problem. Examples of up-to-the-minute information agents will receive include:

• Issues that are trending on social media.
• Topics customers are currently calling about the most.
• Recent updates to products or services.

Real-time speech analytics technology, combined with information being fed to agents in the moment, means that the customer support offered will be tailored to the individual.

Management can program speech analytics to choose agent scripts based on specific speech cues. Software is able to identify words and phrases that are present as well as those that are absent. The software also takes into account sentiment; the point in a call when a word or phrase is said; and the absence of a word or phrase when it should have been said. On top of improving the course of a call while an agent is on the phone, speech analytics can also pinpoint larger gaps in training and find areas for improvement.

The best speech analytics technology will understand the context of a conversation in order to appropriately guide the agent. Customer calls are analyzed in real-time and conversational indicators make it possible for agents to proactively handle a call in a way that’s highly beneficial to the customer.

Advanced speech analytics software helps contact centers in a number of ways. It increases first call resolution and improves the customer experience. It monitors agents for regulation compliance and adherence to company policies. Agents can also use real-time speech analytics to recognize and take advantage of sales opportunities.

4 Important Categories of Contact Center Analytics

 

Contact centers collect a lot of data. They can find out what their customers are doing on a daily basis. They can determine what time a customer contacted support and how long their contact lasted. They can listen carefully to conversations and decide if a customer is happy or angry based on certain keywords. All of this data helps the contact center do things like reduce call times and examine agent performance. To be competitive, contact centers have to stay focused on the customer. By keeping track of customer service metrics, contact centers can make decisions based on reliable data.

1. Speech Analytics

Speech analytics help contact centers improve a customer’s phone call experience. Customer service agents are monitored to ensure they’re adhering to scripts and following regulations. This can also pinpoint the areas in which an agent needs additional training. Speech analytics will also segment hard-to-handle calls so that they can be dealt with by a supervisor or an agent with more experience. Furthermore, speech analytics can determine the reason for the customer’s call, what they hope to get out of the call, and if they are happy, upset, stressed, satisfied, etc.

2. Interactive Voice Response (IVR) Analytics

Intuitive IVR systems improve the customer experience. Insights that can be gleaned from IVR analytics include the percentage of callers who want to speak with a live agent and their reason for doing so; the reason for the transfer of calls between departments; the percentage of callers who were not identified accurately; and the number of calls that were handled from start to finish by IVR.

3. Overall Customer Satisfaction

Gauging overall customer satisfaction will give you an idea of how well you’re delivering the entire customer experience. In order to measure customer satisfaction, the CSAT score is often used. The contact center will ask the customer to rate their satisfaction with a specific experience, like an interaction with the company or a transaction. For example, the customer may be asked to rate their satisfaction on a scale of one to ten. Any answer that’s a six or above means the customer is satisfied. To figure out the percentage of satisfied customers, the number of customers who responded with a satisfied rating is divided by the total number of customers who were surveyed.

4. Predictive Analytics

Tracking analytics isn’t worth much if you’re not going to take the information and figure out how to improve the contact center. Predictive analytics show the changes that will most impact the performance of the contact center. Management can then figure out the best way to communicate with customers, retain happy customers and resolve problems with dissatisfied customers.

One single metric will not give you a useful view of customer service quality. Instead, several metrics that are carefully chosen based on your customer service goals have to be followed. Tracking analytics allows the contact center to improve, update and revamp their programs on a regular basis.

3 Speech Analytics Myths You Should Stop Believing

The number of misconceptions about speech analytics (SA) are surprising, especially considering that even people who currently use SA technology believe the myths. While the learning curve for SA is steep, understanding that the following notions are false will be a big help. When you know how SA does and does not work, you’ll be able to better utilize to its potential.

Myth #1: It’s Not Necessary to Listen to Actual Calls

It’s not possible to simply guess at the voice of the customer and you won’t be able to set useful SA settings if you don’t first listen to real recorded calls. The only way to figure out which business intelligence will be most useful to your company is to listen to a random selection of recordings from a specific queue. As you dissect recordings, you should do the following:

• Map call types for specific objectives.
• Listen to how things are said, not just what is said.
• Create a ranking of keyword categories.
• Identify issues that could cause trouble with the software (transfers, hold music, pre-recorded messages).
• Interpret dialects, accents and colloquialisms.

While listening to numerous calls from beginning to end is tedious, it’s the best way to figure out which words and phrases are most meaningful when it comes to customer intent and outcomes.

Myth #2: Speech Analytics Are a Set-and-Forget Solution

SA make it easy to locate keywords and phrases, but that ability alone isn’t going to give you valuable insight. SA software has to be optimized in order to provide useful and actionable intelligence, taking into account things like the relationship between content and context or specialized language for certain industries. Furthermore, the data you glean from SA won’t be helpful if it isn’t accurate. In order to make sure that the software is at its optimal level of accuracy detection, the speech engine has to be calibrated, tested and tuned until perfect. To do this, search results have to be audited several times over until the speech engine is in harmony with your business objectives. The setup and interpretation phases may be time-consuming and even challenging, but they’re necessary.

Myth #3: Anybody Can Manage Speech Analytics

SA may run automatically, but the software has to be managed on a regular basis, too. There are a range of tasks that must be completed in order to keep SA performing well. While you may have a staff member who’s qualified to take on this role, it’s important to know what’s expected of the person in charge:

• Software setup
• Server and database management
• Compilation, analysis and delivery of key findings
• Content review

One or more people can take on this role. Since the various steps call for different skill sets, some companies opt to split up the role into three parts

1. Administrator for setup and management.
2. Business Analyst for choosing and delivering key findings.
3. Interactions Monitoring Analyst to review content.

Whoever is in charge of SA has to analyze and communicate the findings, explaining why and how changes should be made.

In order to get the most out of SA, it’s important to control your expectations. SA software doesn’t rely on omniscience. Instead, it’s a smart, calibrated filter that shows you the parts of calls that relate to your specific business issues. SA software provides the tools you need to uncover actionable business intelligence. Without it, it would be nearly impossible to find these subtle points of a conversation. With it, you can apply sophisticated strategies to work toward your business objective.