April 2016: We have removed Qualtrics from our experimental workflow, and have instead chosen for a custom Drupal based survey engine. As time went by we needed more and more workarounds to get our code …
Online continuous decoy optimization
Decoy Effect LiF simulation in R
We ran the R simulation below to test our hypothesis that LiF should be able to optimize decoy effects (I will add comments further clarifying my train of thought as reflected by the script within …
The lock-in whiteboard session
Now that we had successfully run some more simulations with Davide’s and Maurits’s lock-in feedback algorithm, we still needed to decide which real life problems might be the most conductive to LiF’s optimum finding prowess. …
StreamingBandit
I recently added an implementation of our Lock-in Feedback algorithm to StreamingBandit. StreamingBandit was originally developed by Maurits Kaptein and Jules Kruijswijk as “a Python Tornado based asynchronous web server to quickly setup and evaluate …