Page 393 -

Chapter 9 Business Intelligence Systems
392

Figure 9-21
Market-Basket Analysis
at a Dive Shop
Source: © Access 2013, Microsoft
Corporation

sold. For example, the 270 on the diagonal cell for Masks means that 270 of the 400 transac-
tions included masks. The 120 in the diagonal cell for Dive Computer means that 120 of the 400
transactions included dive computers.
We can use the number of times an item sold to estimate the probability that a customer
will purchase an item. Because 270 of the 400 transactions were masks, we can estimate the
probability that a customer will buy a mask to be 270/400, or .675. The probabilty of selling a dive
computer is .3.
In market-basket terminology, support is the probability that two items will be purchased
together. To estimate that probability, we examine sales transactions and count the number of
times that two items occurred in the same transaction. For the data in Figure 9-21, fins and masks
appeared together 250 times, and thus the support for fins and a mask is 250/400, or .625.
Similarly, the support for fins and weights is 20/400, or .05.
These data are interesting by themselves, but we can refine the analysis by taking another
step and considering additional probabilities. For example, what proportion of the customers who
bought a mask also bought fins? Masks were purchased 270 times, and of those individuals who
bought masks, 250 also bought fins. Thus, given that a customer bought a mask, we can estimate
the probability that he or she will buy fins to be 250/270, or .926. In market-basket terminology,
such a conditional probability estimate is called the confidence.
Reflect on the meaning of this confidence value. The likelihood of someone walking in the
door and buying fins is 250/400, or .625. But the likelihood of someone buying fins, given that he
or she bought a mask, is .926. Thus, if someone buys a mask, the likelihood that he or she will also
buy fins increases substantially, from .625 to .926. Thus, all sales personnel should be trained to
try to sell fins to anyone buying a mask.
Now consider dive computers and fins. Of the 400 transactions, fins were sold 280 times, so
the probability that someone walks into the store and buys fins is .7. But of the 120 purchases