Re: Data science, data analytics using XSLT streaming

On Tue, Nov 5, 2013 at 5:44 PM, Michael Kay <mike@xxxxxxxxxxxx> wrote:
> This can be
>> compounded by non-technical issues such as data owners not seeing the
>> information they actually have because they are blinded by their
>> expectations of what it is "supposed" to be.
>>
>
> Sometimes the data owners are better clued-in than the technicians. I
> remember a friend who was the IT director of a supermarket chain telling
> me (about 20 years ago, when data analytics had a different fashionable
> name) about a sales presentation he had just sat through telling him all
the
> wonderful things he could do with the data from his tills. His remark:
> "What I really want to know is what the customer didn't buy because it
> wasn't on the shelves. They don't seem to realise that we haven't got
> that data."
>

This can be gotten using techniques similar to how they can recommend
books you haven't read and movies you haven't seen.

"Many firms use decision tools called automatic recommendation
systems that attempt to analyze a customers purchase history and
identify products the customer may buy if the firm were to bring these
products to the customers attention. Much of the research in the
literature today attempts to recommend products that have a high
probability of purchase (conditional on the customers history). ......

ANAND V. BODAPATI*
Journal of Marketing Research
Vol. XLV (February 2008), 7793
77
) 2008, American Marketing Association"