Stanford Computational Antitrust cover image

Episode 1: Gleaning Insight from Antitrust Cases Using Machine Learning (Massarotto & Ittoo)

Stanford Computational Antitrust

00:00

How Much Did the Experiment Cost You?

The machine learning reads only numeric and categorical variables. So initially we thought to add for example among the variables market or market shares but we had two challenges. First it was difficult to identify the relevant market and the market shares in most of FTC consent orders and complaints. Second when the market was defined it was narrowly defined so it appeared only in a case or two. statistically this variable was irrelevant so meaningful less for our machine learning system.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app