The power of analytic technologies

October 3, 2007 at 3:42 pm 1 comment

As you may know, thousands of calls go through a call center everyday. Many calls contain valuable information for the business including agent traits, customer behaviors, competitors’ movements and so forth. Just imagine how much effort management team, supervisors and analysts must spend striving to listen to a massive number of calls in order to find out concerning information. That’s such a time consuming job, right? Thank goodness, we now have analytic technologies helping us in this tough job.


  • Speech Analytics

Speech analytic solutions are currently based on two following technologies:

– Speech-to-text: technology to transcribe recorded audio to text.

– Phoneme-based: technology to identify strings of phonemes and index them.

With transcribed recordings and phonemes’ index, system provides user option to search for words or phrases in the calls. Calls can be tagged with attributes based on combinations of phrases or words in the script texts. These tags can be input information for compliance management, trend analy

sis, root cause analysis and so forth.

Do you believe that an emotional calls can be detected here? Yes, speech analytics can do that for you. Basing on occurrences of words or phrases, the system can point out which call is emotional, which is a sign of bad call handling skills or of something about customer’s behavior should be noticed.

  • Screen Analytics

Screen analytic solutions are using to capture and interpret on-screen activities technology. What takes place on an agent’s desktop can be valuable information to identify attributes of a call or behaviors

of customers or agents. This solution provides user option to “teach” system how to recognize events happen on screen. The same as speech analytics, calls can be tagged with some attributes based on events recognized by the system.

  • Data Mining

Along with script texts and events got from speech and screen analytics, customer feedbacks is also an input for data mining. The data mining technology will scan and find patterns in call data which maybe not obvious to user but indeed the reason of effectiveness or ineffectiveness in the business.

Examples of mining results:

  • Why is call handling time much lower on weekends than weekdays for caller requesting information about a new product?
    • Because agents are telling customers to call back on Monday.
  • Why is there an increase in emotional calls?
    • Account holders are calling to complain about a lower fee schedule available only to new customers as part of a new account promotion.

With these findings, root causes, which answer the “why” questions, are emerged. The solution can also estimate impacts of these causes on the mission achieving goals of the company.

The results…

The power of analytic technologies

So, at the end of the day, data are transformed into actionable business insights thanks to the analytics technologies:

  • Supervisors will only have to listen to calls that are matter most and identify which agents need more training.
  • Management will know what is going on and why that happens and therefore actions can be taken to improve the business performance. Moreover, they can also prioritize what to do first basing on estimated impacts.


With great thanks to:


Gideon Schipper – Business Analyst Manager – First Consulting Group Vietnam


Tai Tran – Business Analyst – First Consulting Group Vietnam

Entry filed under: Business Analyst, CRM.

Describing Facial Features Equip yourselves with useful and important information

1 Comment Add your own

  • 1. Assissotom  |  January 17, 2008 at 12:30 pm

    WOW, so much stuff here, an excellent resource. Thanks guys!


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

Trackback this post  |  Subscribe to the comments via RSS Feed

%d bloggers like this: