Guest post by Bill Inmon
Bill Inmon “is an American computer scientist, recognized by many as the father of the data warehouse. Inmon wrote the first book, held the first conference, wrote the first column in a magazine, and was the first to offer classes in data warehousing.” -Wikipedia.
Ask any executive if they know what’s going on in their call center, and they’ll assure you they are in control and they know what’s going on. (Executives are always in control and always know what is going on, or so they say.) Then ask the executive what’s actually taking place in the call center, and the executive will say, "We get 10,000 calls each day, and the calls last for 4 ½ minutes."
Press the executive a little more: "What are your customers actually saying? What questions do they have? What complaints do they have? Do they want to buy something else? Are they happy with your service?" This is where the executive draws the line.
"Well, you can’t know what the customer is actually saying. You can’t just go into the details of each call."
Okay… but isn't what the customer is saying in the call center — the whole reason they called to begin with — isn't that really important? Isn’t hearing the voice of the customer an extremely valuable thing to do?
What the Customer is Saying
Just a few items customers may call in to talk about include:
- Installation questions and problems
- Incorrectly working products
- Service failures or service delays
- Suggested improvements
- Additional products the customer is interested in
In other words, the voice of the customer is one of the most important things company management can hear. Yet very few, if any, companies pay any real attention to what the customer is saying. Or, at least, that's how it used to be.
Challenges in Today's Call Centers
In today’s business world, technological advances allow companies to hear what the customer is saying in the call center (and everywhere else if executives choose to listen).
But challenges still remain:
- There are always a lot of messages.
- The messages are in the spoken word.
- Voice-to-text transcription is less than perfect.
- Putting text into a database is an act of modern sorcery.
- Creating meaningful visualizations is an art form.
Modern companies are meeting these challenges and garnering really exciting results.
Let's take a closer look at these challenges, however.
Challenge #1. Voice-to-text transcription
Even under the best circumstances, a voice-to-text transcription contains errors. In the most extreme cases, manual transcription can be done, and it's possible to achieve 99% accuracy. But, manual transcription is very expensive and very time-consuming.
The best bet is an automated transcription service, like Otter.ai. Automated transcription costs much less but is more prone to errors. While achieving up to 90% accuracy with automated transcription is possible, even in the best circumstances, there will be inaccuracies.
Inaccuracies in transcription arise because of regional accents, poor call connection quality, low voice modularity, and so forth. It's worth noting that even when people listen to each other face to face, there is no such thing as 100% accuracy of comprehension. In human conversation, the brain automatically tries to fill in the expected word or the word that makes the most sense if a word is not heard correctly. So, expecting 100% accuracy in voice transcription is an unreasonable expectation.
Challenge #2. People speak differently than they write
What may be a normal, comprehensible conversation between two people would never pass muster if the very same words were written and graded by an English teacher. Speaking is something we do so naturally and instinctively that we don’t even know that we speak differently than we write.
The challenge with a call center is that not only must a call center representative deal with language variations but transforming a call center conversation also has to manage the differences between a spoken and written conversation.
Challenge #3. Taking a textual conversation and representing it in a database
After the voice-to-text transcription is complete, the next step is to read the electronic text, make sense of it, edit where necessary, and place the text meaningfully into a database. The hard part of the text-to-database transformation is understanding context.
Text is not meaningful unless you understand that context. The problem with context is that the vast majority lies outside the text itself. In order to be effective, the external influence of context must be interjected into the text.
The good news is that there's technology that performs text-to-database transformation today. The process of automatically reading text and turning text into a database is called textual disambiguation. After the voice is transformed into electronic text, textual disambiguation is used to transform the text into a database, where both text and context are equal partners in the database.
Some of the important elements of the database include:
- An awareness of politeness (or impoliteness)
- An awareness of red flag terms
- An awareness of important business terms
Challenge #4. Scanning the database and converting it to a visualization
Today's dashboard technology is quite useful in converting written databases from a call center into a meaningful visualization.
There are many ways you can examine and visualize call center data, such as:
- By date and time
- By geography
- By general nature of the conversation
- By subject matter
Each of these divisions of customer conversation data yields valuable insights.
How Does It Work?
The dashboard example recreates a telephone company responsible for handling more than 75,000 call center activities daily. That's far too many calls each day for a human to process manually. So, the calls were examined by textual ETL and loaded into a database. Then the database was visualized.
The top left of the dashboard is a general synopsis of the call types conducted. On the bottom right is an hour-by-hour analysis of the number and type of calls entering the system. Above the hourly analysis is a weekly analysis and above that is a monthly analysis. The center of the dashboard is an analysis of what subjects the callers were thinking about.
This dashboard allows for a drill-down analysis on each of the topics. For example, you can ask:
- How many calls came in at 9:00 am?
- How many of the 9:00 am calls were complaints?
- Of the 9:00 am complaint calls, what were the complaints regarding?
Or you can go to the subject analysis section and ask what people talked about with the call center; what were they saying?
One glance at this dashboard shows management a real-time synopsis of how things are going with call center activities. If management finds something of interest, they can drill down to greater detail.
How Forest Rim Tech and Integrate.io Can Help
Listening to the voice of the customer is one of the most important things a company can do. Listening to the customer through the call center using textual visualization is extremely valuable.
There are challenges throughout the process, such as:
- Voice-to-text transcription accuracy
- Textual disambiguation in turning text into a database
- Capturing the context of text
- Visualizing the end results
Bill Inmon, the father of the data warehouse, has authored 65 books and was named by Computerworld as one of the ten most influential people in the history of computing. Bill’s company, Forest Rim Technology, is a Castle Rock, Colorado company. Bill Inmon and Forest Rim Technology provide a valuable service to companies, helping organizations hear the voice of their customer. See more at www.forestrimtech.com.
While challenges exist, they can be overcome with a strong ETL platform and blazing-fast change data capture (CDC) like Integrate.io offers. With reverse ETL and deep Ecommerce capabilities, Integrate.io can help you manage nearly any project. Schedule an intro call to learn more.