Have an idea?

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

Preference for feature combinations (MBC)


We have conducted an MBC exercise with 15 attributes (each tested across 5 price levels).

For analysis - we have created 15 models to predict the choice of the attributes using HB regression.

Is there a method to calculate the preference for a combination of the 15 features?

asked May 10, 2022 by anonymous

1 Answer

0 votes
If I'm understanding correctly, you have 15 dependent variables (each tested across 5 prices) and you want to be able to create market simulations that predict combinations of choices (combinatorial predictions).  That involves making sure you estimate each model using the HB approach in our MBC software.  Then, it involves following the instructions in Chapter 10 of our MBC documentation for simulating combinatorial preferences.

Here's our documentation, hope this direction helps!:  https://sawtoothsoftware.com/resources/technical-papers/mbc-menu-based-choice-documentation
answered May 10, 2022 by Bryan Orme Platinum Sawtooth Software, Inc. (201,565 points)