data science Using transaction data to set priors for message timing experiments If we can form some reasonable assumptions before we ever run an experiment, we can explore the timing landscape more efficiently and move on to exploitation of findings.
experimentation Why you need connected experiments In the previous post, I wrote about the need to structure experiments in a very specific way to keep your results trustworthy. In this post, I’m going to talk
experimentation A walk through our conditioned experimentation process Bokeh.set_log_level("info");We explained our approach to designing “conditioned” experiments in a previous post. Briefly: humans are complicated so if you want experiment results that don’t
data science Machine learning isn't enough I’ve worked as a data scientist for over a decade, much of that time spent on training, testing, and calibrating machine learning models to address specific business problems at
