Analytics 2012: From big data to big buffets


The Analytics conference wrapped up another successful year. One of the last things I did in Las Vegas was decompress with some colleagues at the Bacchanal buffet at Caesar’s Palace. It is, in a word, Bacchanal.

Now back to the meat of the conference. The keynote from William Hakes was one of the most exciting talks I have seen about why companies must get on board with advanced analytical methods for big data. Hakes, from Link Analytics, was engaging and had a compelling message. The talk is recorded. If you have a few minutes, check it out. Good stuff.

I attended two excellent breakout sessions the last day of the conference, each a case study in which the presenter recovered great sums of money for their respective companies. The first was by Lauren Gilmore of the Southern Company who told us about a model her team developed for recovering payment from delinquent accounts. A memorable moment in that talk was when she showed us an equation with an inverse logit function and lots of predictors that she had presented to a non-technical executive. “He loved it,” she told us. “[The executive] said, ‘This is just math! All I have to do is put in some variables and I get a prediction? Wow!’ ”

I need to use that quote the next time a non-technical person balks at one of my own equations: “Hey, it’s just math!” I love it.

The other talk was by Brenda Slagle at Highmark. She presented a model she developed for recovering Medicare revenue for cases with missing diagnosis codes. She demonstrated a net savings improvement of over $11 million compared to an old approach. What impressed me, more than the massive savings to her company, was the way she clearly explained the problem she addressed with her project, the old approach, her (new) approach, the data preparation and analytical methodologies she employed, and the results, with comparisons to other ways to address the problem.

Both of these speakers struck me as people with bright futures in analytics. Which, according to our speaker from Link Analytics, is the best place to be for the next few decades.

By the time the macaroons digested, the real work started for my department. At the end of the conference, over 200 bright professionals signed in for three days of post-conference training classes. I was one of the teams managing the computers for the lab. Anyone who understands Bernoulli counting problems will appreciate that the probability of any one computer having trouble is very small, but the probability of at least one having problems is very, very high. It’s always an adventure!

That’s all for now!


About Author

Catherine Truxillo

Catherine Truxillo, Ph.D. has been a Statistical Training Specialist at SAS since 2000 and has written or co-written SAS training courses for advanced statistical methods including: multivariate statistics, linear and generalized linear mixed models, multilevel models, structural equation models, imputation methods for missing data, statistical process control, design and analysis of experiments, and cluster analysis. Although she primarily works with advanced statistics topics, she also teaches SAS courses using SAS/IML (the interactive matrix language), SAS Enterprise Guide, SAS Enterprise Miner, SAS Forecast Studio, and JMP software. Before coming to SAS, Catherine completed her Ph.D. in Social Psychology with an emphasis in Statistics at The University of Texas at Austin. While at UT Austin, she completed an internship with the Math and Computer Science department's statistical consulting help desk and taught a number of undergraduate courses. While teaching and performing her own graduate research, she worked for a software usability design company conducting experiments to assess the ease-of-use of various software interfaces and website designs. Cat's personal interests include triathlon, hiking the woods near her home in North Carolina, and having tea parties with her two children.

Leave A Reply

Back to Top