August 26th 2014
Wise Practitioner – Predictive Analytics Interview Series: Sameer Chopra of Orbitz
By: Eric Siegel, Founder, Predictive Analytics World
In anticipation of his upcoming conference keynote at Predictive Analytics World Boston, “Blackjack Analytics: A Surprising Teacher from Which All Businesses Can Learn,” we asked Sameer Chopra, GVP of Advanced Analytics, Orbitz Worldwide, a few questions about his work in predictive analytics.
Q: In your work with predictive analytics, what behavior do your models predict?
A: We have predictive models for various applications. For instance:
- In the CPC (cost-per-click) online marketing channels we have response models to predict the Revenue Per Click (RPC).
- We have user level purchase-propensity models (i.e. the likelihood of Eric transacting on Orbitz in say the next 24 hours – vs. Sameer transacting). As you can imagine, this can be an effective lever to use real-estate on our site effectively (eg: whom to show ads to, as a simple use case).
- We also have models to predict user-attrition. Unlike industries with black & white subscriber models, we live in the gray — so a tool like Survival analysis can be a helpful friend.
- We also have built credit-card fraud models.
- I should highlight that we do actively test uplift models to get smarter about segments to pursue and whom not to. etc.
These are just some examples of the different models in play.
Q: How does predictive analytics deliver value at your organization? What is one specific way in which it actively drives decisions?
A: There are numerous areas where PA is driving value. One specific example where it actively drives decisions is in online marketing: determining how much to bid in CPC channels such as Google Adwords, Google Hotel Price Ads (HPA), or Travel Research partners such as TripAdvisor etc.