
IBM Analytics29

















Q #1 : What are best practices in predictive customer analytics?

IBM Analytics
Please post your comments here!

Bob E. Hayes
Integrate data silos; pick a reliable, valid metric.

jameskobielus
For starters, you need to aggregate accurate customer data in order to build statistical models that drive valid predictions.

Sam Hurley ➤➤➤➤➤➤➤➤➤
Recognise success and failure as you begin data crunching. Know when to draw the line in experimentation.

Kirk Borne
I agree with B.O.B. Break down those data silos and integrate data across all biz units (sales, marketing, call center,...)

Kirk Borne
Also, accept fast-fail as a best practice -- try things, low hanging-fruit, quick wins, and quick fails. Learn from all.

jameskobielus
You also should be building segmentation models according to key features/attributes--income, socioeconomics, education, geography, etc.--that describe customer behavior.

Kirk Borne
Thanks you @jameskobielus -- segmentation is key, especially hierarchical models http://syntasa.com/t...

jameskobielus
Clarify what exactly you'll be trying to predict: churn, upsell, etc.

Kirk Borne
As in any #datascience project, start with your business questions and goals. (As @jameskobielus has said :)

Bob E. Hayes
Yes to @jameskobielus. You need to identify your problem area. Pick your outcome measures to match your biz needs.

jameskobielus
Identify the key analytic apps within which those predictions will deliver value--such as marketing campaign optimization, recommendation engines, etc.

Kirk Borne
I agree with @Sam___Hurley -- know when to stop cutting bait and start fishing. Avoid paralysis of analysis.

Bob E. Hayes
I see too many companies simply pick the NPS as the measure of customer loyalty. There are other, better measures to predict other types of loyalty behavior (e.g., stay, upsell).

Sam Hurley ➤➤➤➤➤➤➤➤➤
Thanks @KirkDBorne! An endless experiment never concludes anything...

IBM Analytics
Time for question number 2 at the top of your screen.

jameskobielus
Identify the range of customer data sources--structured plus unstructured (e.g, internal emails, customer feedback and even comments). Define pipeline for consolidating, preparing, sampling, and staging them for downstream analytics

Craig Brown, Ph.D.
I use score cards with real-time customer data that are constantly updated with real-time input.