Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS
FAQ for Eric Siegel’s New Book, “The AI Playbook”
  There are plenty of questions to answer about...
Announcing Eric Siegel’s New Book: The AI Playbook
  Dear Reader, I’m excited to announce the forthcoming,...
Predictive Analytics for the Call Center
 So, you just received your shiny new smart watch....
MLW Preview Video: Gulrez Khan, Data Science Lead at PayPal
 In anticipation of his upcoming keynote presentation at Predictive...
SHARE THIS:

5 months ago
The Science of Price Experiments in the Amazon Store

 
Originally published in Amazon Science, April 14, 2023.  

The requirement that at any given time, all customers see the same prices for the same products necessitates innovation in the design of A/B experiments.

The prices of products in the Amazon Store reflect a range of factors, such as demand, seasonality, and general economic trends. Pricing policies typically involve formulas that take such factors into account; newer pricing policies usually rely on machine learning models.

With the Amazon Pricing Labs, we can conduct a range of online A/B experiments to evaluate new pricing policies. Because we practice nondiscriminatory pricing — all visitors to the Amazon Store at the same time see the same prices for all products — we need to apply experimental treatments to product prices over time, rather than testing different price points simultaneously on different customers. This complicates the experimental design.

In a paper we published in the Journal of Business Economics in March and presented at the American Economics Association’s annual conference in January (AEA), we described some of the experiments we can conduct to prevent spillovers, improve precision, and control for demand trends and differences in treatment groups when evaluating new pricing policies.

To continue reading this article, click here.

3 thoughts on “The Science of Price Experiments in the Amazon Store

Leave a Reply