The original is misleading, unless we know what you are talking about. If
you are saying there's a rule
e-books -> software
With support 1% and Confidence 50%. This means that 1% of the transactions
have e-books, and 50% of the transactions that have e-books also have
software.
Now if you are saying there's an itemset
e-books, software
with support 1%, this means that 1% of all transactions contain both e-books
and software. Confidence has no meaning for itemsets.
--
-Jamie MacLennan
SQL Server Data Mining
This posting is provided "AS IS" with no warranties, and confers no rights.
[quoted text, click to view] <jackso95@hotmail.com> wrote in message
news:1129437214.825517.265750@g49g2000cwa.googlegroups.com...
> The following was taken from a posting in the forum discussing the
> APriori algorithm. Can someone clarify for me the value used to for
> this calcualtion. I guess the best way to ask my question is the use
> the statement that was posted.
>
> Original:
> Support measure of 1% and a Confidence measure of 50% means that 1% of
> transactions analyzed contain purchases of e-books and software and 50%
> of customers who bought an e-book also bought a software.
>
>
> Should this read???
> Support measure of 1% and a Confidence measure of 50% means that 1% of
> transactions analyzed (?? ALL transactions for the time period being
> analyzed ??) contain purchases of e-books and software and 50% of
> customers (?? ALL customers for the time period being analyzed ??) who
> bought an e-book also bought a software.
>
> OR Should this read???
> a Support measure of 1% and a Confidence measure of 50% means that 1%
> of transactions (?? ONLY those transactions were an e-book was
> purchased ??) analyzed contain purchases of e-books and software and
> 50% of customers (?? include only those customers who purchased an
> ebook ??) who bought an e-book also bought a software.
>
> Thanks.
>