Chris Crosby

Speech Recognition is about identifying what people are speaking.

Speech Analytics is about figuring out what people are saying.

I came across a clever demonstration of Analytics from a Business Intelligence software provider called QlikView, and thought it worth sharing. Note- In an indirect way, Latigent competed with QlikView and I always admired their clever marketing campaigns. In this application of their analytics tool, they dumped radio airplay data from  MediaGuide.com into an OLAP cube and overlayed the QlikView front end (demo found here).

Originally I just wanted to play around with the data, so I filtered based on the greatest band of all time, Van Halen.

Unexpectedly, a couple of things struck me about the results:

1. The top two most played songs both appear on the album 1984, but 1984 is the second most played album: Seems a bit counter intuitive at first, but upon closer inspection we discover that the album Van Halen’s songs may be played fewer times, but there are more of them. The aggregate is greater by more than 300 song plays. There is a lesson to be learned here about product distribution, and a pretty good example of Chris Anderson’s Long Tail theory in action.
2. Why the big disparity between the “David Lee Roth Van Halen” and the “Sammy Hagar Van Halen”? My assumption is that this is most likely because Van Halen is on tour right now with David Lee Roth. No doubt radio stations are heavily promoting this tour by spinning the vintage favorites. My hypothesis though is one that is impossible to prove given the current data set. One would “just need to know” that these guys are on tour to draw that conclusion. Without this information, what conclusions would you draw? Would they be accurate? Is mine accurate?

Now, an interesting exercise would be to take the chart below that displays where these songs are being played and overlay the tour schedule. Also, the data is only available from Feb 24, 2007 to current. What would a wider data set show us? Is the distribution reversed when they’re on tour with Sammy Hagar? What about when they’re not on tour?

This example demonstrates that the unlocked power of analytics is not just about spotting trends that you otherwise would not have, but its often in finding and qualifying external (and sometimes non-structured) data points and quantifying their impact. It also causes you to ask questions and seek answers that you otherwise wouldn’t: What long tails are hiding in your data? How can you leverage them? What external events influence your business? How do you qualify them, and quantify their impact?

What else do you not know you need to know?

Looks like Pentaho closed a $12M Series C round of financing. This is exciting stuff. With the consolidation of large Business Intelligence players its opening the market for the already under served SMB and for Enterprise BI projects looking for a lower cost of ownership.

The only real question is if these guys will join the ranks of Zimbra and become a promising start-up swallowed by a behemoth too soon…

“The process of discovering what you don’t Know you need to Know.”

-Chris Crosby

OK, so the title is a bit overstated, but now that I have your attention:

A couple months ago Google [quietly] released a hosted charting API. Albeit it lacks the sex appeal of their big splash products like GMail or Google Docs, it tapped my imagination.

The basic concept is that your application passes parameters to a URL hosted at Google. It allows you to define things like chart type, size, colors, data values, etc. For example, hitting this URL,

 http://chart.apis.google.com/chart?cht=p3&chd=s:hW&chs=250×100&chl=Hello|World

returns the following image:

Part of the reason this grabbed my attention is that its very similar to Latigent’s BlueVue (now Cisco Unified Intelligence Suite ((CUIS))) “API” for accessing reports & charts from other applications (except you don’t actually pass the data to CUIS, since that’s the real point of having a full blown BI App What I find amusing here is that Google, whether intentionally or not, has basically entered into the 3rd party control business. Very few people ever build their own charting control as its not core to their application, and there are inexpensive alternatives to coding your own. Google just introduced another inexpensive option. Now, I seriously doubt that Google will ever cut into the market share of guys like Dundas, but it could certainly address the needs of some low-level apps.

Expanding on this hosted API/3rd Party Control concept, it’s reasonable to think that a creative developer could duct-tape together the APIs from Google Docs, Google Maps, Google Charts, Google Reader (unsupported “API” here) and Google Search Appliance to come up with a rudimentary and functional presentation layer for a reporting application.

When you pepper in things like databases in the cloud, one begins to ponder if every aspect of an application will eventually be distributed, and perhaps the next software evolution will be nothing but middleware that glues stuff together.

The last of the large BI acquisition dominoes fell today when IBM announced it’s intention to acquire Cognos for just short of $5b. With Hyperion and Business Objects getting snapped-up by Oracle and SAP respectively, Microsoft "trying" to march its way into BI/Performance Management, and rumors of a Cognos/IBM deal floating around since last year, most of the industry yawned and wondered what took so long for these guys to get to the alter.

From a marriage standpoint, the fit actually seems natural to me and I think its a good thing for both companies’ customers. These guys have been partners for a long time and the product portfolios compliment nicely with little overlap. This one should also keep the IBM Global Services guys raking in cash for awhile.

As far as what that means for the BI industry as a whole, it opens the door for the maturing open source market to prove itself. There is still a growing market in the SMB and with very few established stand alone, truly agnostic players left, this creates a window for guys like Pentaho and Jaspersoft to walk in and plant their flags.

I want to pass along information on a webinar that AC2 Solutions, Latigent’s preferred Workforce Management Partner, is doing later this week. If you have never seen AC2 Solutions products you are truly missing out on the future of workforce management. These guys have a killer solution and a clear vision on where contact centers are going and how you’ll need to forecast and staff for them. 

Dr. Aykin is extremely knowledgeable and regardless of which WFM product you use you won’t want to miss their free events.  

You can register for the webinar here.  Please see below for the description of the event.

Each month, Dr. Turgut Aykin discusses relevant topics in the workforce optimization arena via free web seminars.  Every workforce manager can benefit extensively from Dr. Aykin’s knowledge and experience.
On Thursday September 6, forecasting, probably the most vital step in the workforce management process, will be the topic of discussion. Without a solid forecast in place, the best workforce management systems will falter. While forecasting methodologies range from simple gut feel to intricate mathematical algorithms, there are several that every workforce manager should be aware of to effectively forecast the center’s workload.

In today’s complex multi-skill, multi-site, multimedia contact centers, forecasting contact volumes and average handling times accurately can be an extraordinary challenge.  During this web seminar Dr. Aykin will review several techniques used for forecasting and discuss advantages and risks of each.
Participants will learn about the following:

• Why accuracy in workforce planning matters?
• Time series models
• Exponential smoothing
• Time series decomposition
• Box-Jenkins ARIMA Models
• Dynamic regression
• Curve fitting
• Expert systems for contact center forecasting
• Agent requirements forecasting
• Forecast accuracy tracking
• Overview of upcoming seminar:  Optimal Scheduling (September 21, 3pm ET)

To register, please go to http://www.ac2solutions.com/index.php/about/seminar-registration/

Be sure to join Dr. Aykin on future web seminars as well.

• Advanced Forecasting (Sept. 6, 3pm ET)
• Optimal Scheduling (Sept. 21, 3pm ET)
• Revenue Optimal Staffing & Scheduling (Oct. 4, 3pm ET)
• Safety Staffing (Oct. 18, 3pm ET)
• Multi-criteria schedule Bidding & Vacation Planning (Nov. 1, 3pm ET)

Dr. Turgut Aykin is the president of ac2 Solutions. He has published numerous scientific articles in refereed professional journals on contact center efficiencies, and he has routinely been invited to contribute at national conferences. He has served as an Area Editor and member of the Editorial Board for the International Journal of Information Systems in the Service Sector (IJISSS), and is a member of the International Journal of Operations and Quantitative Management. He has worked with many Fortune 500 companies including Bank of America, Caterpillar, Celestica, Charter Communications, Convergys, Delta Air Lines, IBM, Lucent Technologies, Motorola, Phillips, and Siemens (Munich, Germany) in improving their processes and performance.  Dr. Aykin holds BS, MS, and Ph.D. degrees in Industrial Engineering and Operations Research.

 

I have been asked A LOT lately if the Latigent Business Intelligence Suite provides cradle-to-grave call reporting for Cisco ICM/ IPCC and/or Customer Voice Portal (CVP). The short answer is yes, we do.

Without giving away any of our, or Cisco’s, proprietary techniques you can refer to their Solution Reference Network Design (SRND) for Cisco Unified Customer Voice Portal, Release 4.x which I found with a little help from Google.

BlueVue provides a pretty flexible and easy to use filtering and search tool over Cisco ICM’s call detail data. For example, you can run a report for all calls that meet a certain criteria (I.E. Talk Time > 20 mins, or Abandoned in Queue after 60 mins, etc.), or you can search for a specific call by ANI (caller’s phone number) or ICM Call Variable value. You can also drill-down into what we call the “Call Life Report”, which is basically a formatted and visual picture of what transpired on each leg of the call.

Pretty cool, heh? If you have questions or want to see a demo, give me a shout.