sending offers only to those likely to want the product. Machine
learning can
help companies to find the targets.
Other applications
There are countless other applications of machine learning. We briefly mention
a few more areas to illustrate the breadth of what has been done.
Sophisticated manufacturing processes often involve tweaking control
parameters. Separating crude oil from natural gas is an essential prerequisite to
oil refinement, and controlling the separation process is a tricky job. British
Petroleum used machine learning to create rules for setting the parameters. This
now takes just 10 minutes, whereas previously human experts took more than
a day. Westinghouse faced problems in their process for manufacturing nuclear
fuel pellets and used machine learning to create rules to control the process.
This was reported to save them more than $10 million per year (in 1984). The
Tennessee printing company R.R. Donnelly applied the same idea to control
rotogravure printing presses to reduce artifacts caused by inappropriate
parameter settings, reducing the number of artifacts from more than 500 each
year to less than 30.
In the realm of customer support and service, we have already described adju-
dicating loans, and marketing and sales applications. Another example arises
when a customer reports a telephone problem and the company must decide
what kind of technician to assign to the job. An expert system developed by Bell
Atlantic in 1991 to make this decision was replaced in 1999 by a set of rules
learned using machine learning, which saved more than $10 million per year by
making fewer incorrect decisions.
There are many scientific applications. In biology, machine learning is used
to help identify the thousands of genes within each new genome. In biomedi-
cine, it is used to predict drug activity by analyzing not just the chemical
properties of drugs but also their three-dimensional structure. This accelerates
drug discovery and reduces its cost. In astronomy, machine learning has
been used to develop a fully automatic cataloguing system for celestial objects
that are too faint to be seen by visual inspection. In chemistry, it has been used
to predict the structure of certain organic compounds from magnetic resonance
spectra. In all these applications, machine learning techniques have attained
levels of performance—or should we say skill?—that rival or surpass human
experts.
Automation is especially welcome in situations involving continuous moni-
toring, a job that is time consuming and exceptionally tedious for humans. Eco-
logical applications include the oil spill monitoring described earlier. Some
other applications are rather less consequential—for example, machine learn-
ing is being used to predict preferences for TV programs based on past choices
2 8
C H A P T E R 1
|
W H AT ’ S I T A L L A B O U T ?
P088407-Ch001.qxd 4/30/05 11:11 AM Page 28
and advise viewers about the available channels. Still others may save lives.
Intensive care patients may be monitored to detect changes in variables that
cannot be explained by circadian rhythm, medication, and so on, raising
an alarm when appropriate. Finally, in a world that relies on vulnerable net-
worked computer systems and is increasingly concerned about cybersecurity,
machine learning is used to detect intrusion by recognizing unusual patterns of
operation.
1.4 Machine learning and statistics
What’s the difference between machine learning and statistics? Cynics, looking
wryly at the explosion of commercial interest (and hype) in this area, equate
data mining to statistics plus marketing. In truth, you should not look for a
dividing line between machine learning and statistics because there is a contin-
uum—and a multidimensional one at that—of data analysis techniques. Some
derive from the skills taught in standard statistics courses, and others are more
closely associated with the kind of machine learning that has arisen out of com-
puter science. Historically, the two sides have had rather different traditions. If
forced to point to a single difference of emphasis, it might be that statistics has
been more concerned with testing hypotheses, whereas machine learning has
been more concerned with formulating the process of generalization as a search
through possible hypotheses. But this is a gross oversimplification: statistics is
far more than hypothesis testing, and many machine learning techniques do not
involve any searching at all.
In the past, very similar methods have developed in parallel in machine learn-
ing and statistics. One is decision tree induction. Four statisticians (Breiman et
al. 1984) published a book on Classification and regression trees in the mid-1980s,
and throughout the 1970s and early 1980s a prominent machine learning
researcher, J. Ross Quinlan, was developing a system for inferring classification
trees from examples. These two independent projects produced quite similar
methods for generating trees from examples, and the researchers only became
aware of one another’s work much later. A second area in which similar methods
have arisen involves the use of nearest-neighbor methods for classification.
These are standard statistical techniques that have been extensively adapted by
machine learning researchers, both to improve classification performance and
to make the procedure more efficient computationally. We will examine both
decision tree induction and nearest-neighbor methods in Chapter 4.
But now the two perspectives have converged. The techniques we will
examine in this book incorporate a great deal of statistical thinking. From the
beginning, when constructing and refining the initial example set, standard sta-
tistical methods apply: visualization of data, selection of attributes, discarding
1 . 4
M AC H I N E L E A R N I N G A N D S TAT I S T I C S
2 9
P088407-Ch001.qxd 4/30/05 11:11 AM Page 29