Marketplace Experimentation at SpotHero
Explore marketplace experimentation at SpotHero in this 29-minute conference talk from the Toronto Machine Learning Series. Dive into the challenges faced by the data science team at North America's largest off-street parking reservation platform. Learn about dynamic pricing, marketing, and ranking problems, with a focus on testing machine learning models in production. Discover why traditional A/B testing falls short in their scenario and explore alternative approaches, including switchback experimentation. Gain insights into SpotHero's experiment design, technical architecture, and a real-world example of their experimental results. Join speaker Amish Popli, Data Scientist at SpotHero, as he shares valuable insights on improving key performance indicators in a two-sided marketplace involving drivers and parking garage owners.