Presenter: Sheridan Hitchens, Vice President, Data Products
May 8, 2017
It’s well known that many big data and data science initiatives fail and that the root causes of these failures are myriad. Knowing how other projects fail can help guide you to success by helping you avoid the traps up front. Sheridan Hitchens of Ten-X explores the pitfalls and mistakes companies make — strategically, organizationally, technically, and analytically — as they embark on big data initiatives and presents simple practical solutions to avoid them.
Third Nature, Inc.
May 11, 2017
The story of the correlation between beer and diaper sales is commonly used to justify why analytics is useful in business and to explain product affinities in introductory data mining courses. Rarely does anyone ask about the origin of this story. Is it true? Why is it true? What does “true” mean anyway? The last question is the most interesting because it challenges the ideas of accuracy in data and analytic models. Mark Madsen examines the history of the “beer and diapers” story, explaining its origins and truth, based on repeated analyses of retail data over two decades. Mark will share how multiple contradictory results can come from analytic models and how they can all be true, leading to the questions of the value of “easy-to-use” analytics. The real lesson of the story is that interpretation of the results of analytic models is key, not the data or model. You can’t apply (effectively) what you don’t understand.