Beth Schultz

Ask & Ask Again: Questions Matter in Modeling

NO RATINGS
View Comments: Newest First | Oldest First | Threaded View
MDMconsult
User Rank
Prospector
Re: Asking the right questions
MDMconsult   11/30/2012 6:26:35 PM
NO RATINGS
@Lyndon_Henry I agree, results should accept and help to narrow ideas from being "too broad" Numerous issues can be identified through these surveys. Work with the most problematic issues such as security challenges, internal problems, etc al. It is important to be able to prioritize, act on survey results with needed improvements.

Lyndon_Henry
User Rank
Blogger
Re: Asking the right questions
Lyndon_Henry   11/29/2012 5:27:18 PM
NO RATINGS
..

Beth asks


...so are you suggesting surveying business users/managers about what business problem they're hoping the analytics will help them address? Or are you speaking more generally of surveys, for customer satisfaction, etc.?


 

Well, certainly, surveying the potential users (managers, administrators, planners, etc.) of the results would be a terrific idea.

But I had in general public surveys more in mind — I've had more experience with those.

In either case, you need to try to define the key issues as narrowly as possible.  Otherwise, I think you get survey results that are so broad and mushy they are close to useless (except lots of planners and dcisionmakers like to get results that are so broad and mushy they can interpret them in ways to bolster their own preferred goals).

And if this is supposed to feed into the development of a model, you could really end up with some junk and perhaps a mess.

 

BethSchultz
User Rank
Blogger
Re: Asking the right questions
BethSchultz   11/29/2012 3:22:40 PM
NO RATINGS
@Lyndon_Henry -- so are you suggesting surveying business users/managers about what business problem they're hoping the analytics will help them address? Or are you speaking more generally of surveys, for customer satisfaction, etc.?

Lyndon_Henry
User Rank
Blogger
Asking the right questions
Lyndon_Henry   11/28/2012 11:05:41 PM
NO RATINGS
..

Beth's article asks


Do you ask enough questions during your modeling process? 


 

Where I've found asking (formulating) the right questions to be important has been in surveys.  Not that they've all led to analytical models, but they have influenced decisonmaking, and some have fed into the modeling process.  Learning to ask the right questions is also helpful in learning how to identify the critical variables that are needed to make good decisions and build more effective models.

 

Pierre DeBois
User Rank
Blogger
Re: Answer the question, question the answers
Pierre DeBois   11/27/2012 1:25:02 PM
NO RATINGS
Callmebob, very true.  I like how this seems to really force introspection into the value of what is being modeled. Modeling data that may take too long of an arc to answer relative to the business need could benefit from this structure.

Callmebob
User Rank
Master Analyst
Answer the question, question the answers
Callmebob   11/27/2012 1:15:06 PM
NO RATINGS
Here's where I think that the data wizards need to have a bit of a marketing mind. In fact, they should work in consortium to create models that frame marketing's questions that answer their tasks to identify target markets, market research, product development, marketing mix, and monitoring results.

Information Resources
More Blogs from Beth Schultz
It's been a fun three years, but now it's time to say goodbye.
Take inspiration from Christopher Columbus as you pursue your analytical journeys.
The "big" in big data is no reflection of the size of the organization embracing its potential.
Whether you're an undergrad, a graduate student, or an analytics professional already, the same best-practices advice lives large.
Satellite data can help solve puzzles, from the lofty to the mundane.
Radio Show
Radio Shows
UPCOMING
James M. Connolly
Analytics: Your Defense Against Cyber Threats


5/27/2015   REGISTER   0
ARCHIVE
James M. Connolly
Big Data & Big Pharma: How Analytics Might Save Your Life


5/19/2015  LISTEN   37
ARCHIVE
James M. Connolly
Live Interviews From SAS Global Forum


4/28/2015  LISTEN   11
ARCHIVE
James M. Connolly
How to Hire Great Analytics Talent


4/23/2015  LISTEN   51
ARCHIVE
James M. Connolly
Sports Analytics Mean Fun and Business


3/24/2015  LISTEN   4
ARCHIVE
James M. Connolly
Secure Your Big Data in the Cloud


2/26/2015  LISTEN   114
ARCHIVE
James M. Connolly
Make It Big As a Data Scientist in 2015


2/11/2015  LISTEN   106
ARCHIVE
James M. Connolly
Big Data, Decisions & the Simulated Experience


2/3/2015  LISTEN   87
ARCHIVE
James M. Connolly
A Chat About Big Data, Machine Learning & Value


1/15/2015  LISTEN   125
ARCHIVE
Curtis Franklin Jr.
An Infrastructure for Analytics


12/18/2014  LISTEN   63
ARCHIVE
James M. Connolly
Prepare for the Internet of Things Data Blitz


12/16/2014  LISTEN   51
Information Resources
Quick Poll
Quick Poll
Infographic
Infographic
It Pays to Keep Insurance Fraud in Check
While 97% of insurers say that insurance fraud has increased or remained the same in the past two years, most of those companies report benefits from anti-fraud technology in limiting the impact of fraud, including higher quality referrals, the ability to uncover organized fraud, and improve efficiency for investigators.
Follow us on Twitter
Follow us on Twitter
Like us on Facebook
Like us on Facebook
About Us  |  Contact Us  |  Help  |  Register  |  Twitter  |  Facebook  |  RSS