Have an idea?

Visit Sawtooth Software Feedback to share your ideas on how we can improve our products.

What is the rule/algorithm to find near-neighbor concepts within ACBC?

Hello everyone,

I am wondering if there is a rule or algorithm that SSI Web respectively Lighthouse Studio 9 is using to find near-neighbor concepts for the screening-task after respondents did the BYO-task?

If so, could someone describe the procedure to me?
Thank you of your support!

Regards,
Johannes
asked Oct 28, 2016 by Hansson (270 points)

2 Answers

+1 vote
answered Oct 28, 2016 by Bryan Orme Platinum Sawtooth Software, Inc. (165,215 points)
Dear Orme, thank you so much for your support!
0 votes
The rule first looks at how many attributes it is allowed to change from the BYO task.  It is a random number between Minimum Attributes to Vary from BYO Selections and Maximum Attributes to Vary from BYO Selections. So if the min is 2 and the max is 4 then lets say it randomly chooses 3.  Then it  randomly chooses 3 attributes to modify its levels and changes them including the least changed ones.  The changes are allowed as long as they don't violate prohibitions and alternative specific designs.  If the attributes were not included in the BYO then it will always change that attribute.
answered Oct 28, 2016 by Mike Lodder Gold (23,395 points)
...