Search parameters

When any of the four algorithm based searches are to be used  then the first step is to some parameters about how the search will proceed. These are:

  1. The objective: the performance measure that needs to be maximised. In future it may also be possible to seek minimum values.
  2. The variable values: the project attributes which can be varied in order to best achieve the objective. These are currently set by default as all the attributes in the Design view. This range can be altered by changing the status of individual attributes in the Select data worksheet, from either Ignore to Attribute or Attribute to Ignore
  3. The constraints: the project attributes and possibly also some performance measures, whose values must remain within specified limits. There are ways of setting constraints:
    1. Go to the Design menu and select one or more attributes to have specific values (either 1 or 0)
    2. Go to the Confusion Matrix and select on or two of the cells to have specific values. The three most useful constraint settings here are:
      1. “False Positives = 0” This will help find Sufficient conditions or configurations of conditions.
      2. “False Negatives = 0” This will help find Necessary conditions.
      3. “False Positives = 0 and False Negatives = 0”. This will help find Necessary and Sufficient conditions
    3. Go to the Performance Measures and select a performance measure, such as Lift, and a minimum performance value that you want any solution to meet or exceed.

Note that algorithm based searches can be used in conjunction with Hypothesis led search, by setting some of the attributes of a given hypothesis as a constraint but then exploring “the adjacent possible” in the vicinity of that part of the hypothesis.

Changing the Solver (evolutionary) search parameters

In the background, outside of EvalC3, there are settings which govern how Solver runs. To see and change these go up to the top of the Excel interface and click on Data, then look to the far right and click on Solver. Click on Options, then Evolutionary. For information on all the search parameters listed here, which you can change, see this web page:


Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.