14.6 THE CONFIDENCE DIFFERENCE CRITERION
The association rules above were generated using the minimum confidence criterion. However, other criteria exist for generating association rules. Next, we consider the confidence difference criterion. The confidence difference evaluation measure gives the absolute difference between the prior probability of the consequent (here, churn status) and the confidence of the rule. So, rules would be included in this case only if:
![equation](https://static.packt-cdn.com/products/9781119526810/graphics/images/c14-disp-0014.png)
Figure 14.6 shows the only association rule generated using a confidence difference lower bound of 40 (along with minimum antecedent support of 1%, minimum rule confidence of 5%, and maximum antecedents of 1).
![No alt text required.](https://static.packt-cdn.com/products/9781119526810/graphics/images/c14f006.gif)
Figure 14.6 Association rule found using confidence difference lower bound = 40.
This association rule has Rule confidence 0.59016 and prior probability of Churn = True of 0.14533, giving us:
![equation](https://static.packt-cdn.com/products/9781119526810/graphics/images/c14-disp-0015.png)