1. https://appdevelopermagazine.com/monetize
  2. https://appdevelopermagazine.com/app-monetization-data-science-at-flurry-makes-my-brain-hurt/
4/23/2014 11:19:53 AM
App Monetization Data Science at Flurry Makes My Brain Hurt
app analytics, app marketing, app monetization, mobile analytics
App Developer Magazine
App Monetization Data Science at Flurry Makes My Brain Hurt


App Monetization Data Science at Flurry Makes My Brain Hurt

Wednesday, April 23, 2014

Richard Harris Richard Harris

We all just assume that the inner workings behind companies that are the backbone of the app development industry just work. So naturally we just a assume company like Flurry, that provides mobile analytic data and app marketing/monetization services, knows what its doing to provide its services.

However, recently I stumbled across a blog post by Soups Ranjan, Ph.D. discussing the problems that the data science team at Flurry deals with on a daily basis. Now I didn’t really know they had a data science team at Flurry, but it makes sense to manage the billions of pieces of data that they deal with each month. And I probably should have been warned that as a Ph.D., Dr. Ranjan was going to speak at a few levels above my pay grade.

And his article starts out innocently enough, with his statement, “The most challenging problems that the data science team at Flurry deals with are estimating user characteristics (e.g., age,  gender, and interests of app users) and predicting responses to advertising (and therefore which ads should be served to which people).” 

Ok, that makes sense, but then I started reading further, and all of the sudden, bam, its hard math time and I’m back at my trig class in college. 

I knew I was in for it when I came to his statement, “More specifically, we use Logistic Regression to solve this problem. Logistic Regression is used for predicting the probability of an event. It predicts by fitting the data to a logistic curve. Consider an ad impression Y which has the features defined in a set X= {x1,x2,…, xn}. We define a logistic function f(z)= P(Y=1|X=x). Note that f(z) is 1 when impression Y converts and it  is 0 when it doesn’t convert. We define f(z) = 1/ (1 + exp(-z))where z is a logit and is given as….”

Whew, let me get out my calculator! So why am I telling you this? Because, while my eyes glazed over a bit from time reading the article, it is fascinating to see just a glimpse of what happens behind the scenes at an analytics company like Flurry. So my suggestion to you is to check it out for yourself.

Read more: http://tech.flurry.com/

Subscribe to App Developer Magazine

Become a subscriber of App Developer Magazine for just $5.99 a month and take advantage of all these perks.


  • - Exclusive content from leaders in the industry
  • - Q&A articles from industry leaders
  • - Tips and tricks from the most successful developers weekly
  • - Monthly issues, including all 90+ back-issues since 2012
  • - Event discounts and early-bird signups
  • - Gain insight from top achievers in the app store
  • - Learn what tools to use, what SDK's to use, and more

    Subscribe here