Transcript Intro to Data Mining

Mining Gold from Data
Data Mining
Data Mining

Mining data is all about finding
hidden patterns and relationships in
data

You strike “gold” when you find
patterns in data that give you new
information or help you make
decisions
Can you find the hidden word here ?
How about here?
Or here?
This one’s tough . . .
The human mind is a master at
finding patterns . . .
The phaonmneal pweor of the hmuan mnid,
aoccdrnig to rscheearch at Cmabrigde Uinervtisy,
is taht it deosn't mttaer in waht oredr the ltteers
in a wrod are, the olny iprmoatnt tihng is taht the
frist and lsat ltteer be in the rghit pclae. The rset
can be a taotl mses and you can sitll raed it
wouthit a porbelm.
Tihs is bcuseae the huamn mnid deos not raed
ervey lteter by istlef, but the wrod as a wlohe.
Amzanig huh?
But sometimes the human
mind is wrong . . .
Or the human mind suffers from
information overload . . .
FINISHED FILES ARE THE
RESULT OF YEARS OF SCIENTIFIC
STUDY COMBINED WITH THE
EXPERIENCE OF YEARS . . .
Or the human mind suffers
from information overload . . .
FINISHED FILES ARE THE
RESULT OF YEARS OF SCIENTIFIC
STUDY COMBINED WITH THE
EXPERIENCE OF YEARS . . .
Or sometimes humans don’t
ask the right questions . . .
Or sometimes we’re sorry we
asked ANY questions . . .
Enter Data Mining Algorithms and Software

Data Mining Software . . .

Can detect patterns in data that the human mind cannot
(e.g., finding patterns in Internet blogs to stop terrorists)

Can detect patterns faster than the human mind
(e.g., monitoring credit card activity for fraud)

Can detect patterns when there are too many data to analyze
(e.g., finding patterns in medical data to treat disease)

Can detect patterns and answer questions a human being
would never think to ask
(e.g., beer & diapers!)
Some Data Mining Examples

Amazon.com mines customer purchasing data to suggest
additional purchases to online shoppers (Cobbs, 2006)

Stanford University School of Medicine used data mining to
pinpoint genes involved in diseases, aging, injuries, & muscle
development
(Biotech Week, 2006)

The NSA mines telephone data in search of patterns to identify &
link suspected terrorists (Sternstein, 2006)

Bank of America uses data mining to detect & deter credit card
fraud (Hormazi, 2004)

Fingerhut uses data mining to send over 130 “specialty” catalogs
to targeted customer segments (Hormazi, 2004)

Harrah’s Casinos uses data mining to send over 20 million tailored
offers to its customers on an annual basis (Meltzer, 2004)
The End . . . Happy Mining!