Post on 06-Jan-2017
© 2015, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
October 2015
MBL309
Analyze Mobile App Data and
Build Predictive ApplicationsSandeep Atluri, AWS Data Scientist
What to Expect from the Session
• Collect, analyze, and visualize mobile app data with
Amazon Mobile Analytics
• Run ad-hoc analysis to gain deeper insights with
Amazon QuickSight
• Build predictive applications for your mobile app with
Amazon Machine Learning
RetrospectiveAnalyze historical
trends to know
what's happening in
the app
Predictive Anticipate user
behavior to enhance
experience
InquisitiveDiscover latent user
behavior to shape
product or marketing
decisions
Three Types of Data-Driven Decision Making
How many users use the app and how often?
What are key user behaviors in the app?
Your
Mobile
App
How to predict user behavior and use those
predictions to enhance their experience ?
In the Context of a Mobile App
Three Types of Data Driven Decision Making
RetrospectiveAnalyze historical
trends to know
what's happening in
the app
Predictive Anticipate user
behavior to
enhance experience
InquisitiveDiscover latent user
behavior to shape
product or marketing
decisions
Let’s just say we have built a music app
What are some of the questions that would help us in understanding what’s
happening in the app?
Music App
Engagement
How many users use
the app daily to listen
music ?
How many times
users open the app to
listen music in a day?
How many new users
have been acquired
to the app ?
Monetization
How many paying
users does the app
have ?
How much does a
average paying user
pay ?
Retention
How many people
returned to listen
music in the first 7
days after they
have installed the
app ?
Behavioral
How many users
shared or liked a
particular artist ?
Few Key Questions to Understand Trends in the
App
Amazon Mobile Analytics“Collect, visualize and export your app usage data at scale”
Accurate results
Amazon Mobile Analytics
processes ALL data received to
provide accurate analytics on
your app use. We never provide
reports based on sampled data
even if you are in the free tier.
Your app, your data
Your app data is safe
with us. We don’t report
on or share your data
with third parties.
Focus on metrics that
matter. Usage reports
available within 60
minutes of receiving data
from an app
Fast
Amazon
Mobile
Analytics
Engagement + MonetizationActive UsersSessionsIn-app RevenueLifetime Value (LTV)
RetentionPost-install Retention Funnel
BehaviorCustom Events
RetrospectiveAnalyze historical
trends to know
what's happening in
the app
Predictive Anticipate user
behavior to enhance
experience
InquisitiveDiscover latent user
behavior to shape
product or marketing
decisions
Three Types of Data Driven Decision Making
How does usage pattern vary for users with different demographic profiles?
Who are the most engaged users and what are their usage patterns ?
How does user population distribute across countries and platform ?
How much time does it takes for a user to convert to a paying user ?
Music App
Few Questions That Will Help You Understand
Your Users Better
Simple &
intuitive
Integrate with
existing data
models
Automatically
collect common
attributes
Schema for Your App’s Event Data
RetrospectiveAnalyze historical
trends to know
what's happening in
the app
Predictive Anticipate user
behavior to enhance
experience
InquisitiveDiscover latent user
behavior to shape
product or marketing
decisions
Three Types of Data Driven Decision Making
Let’s say we have been observing high user churn
in the music app. Now, we want to identify these
users in advance so that we could reach out to
users before they leave the app
Predictive Application by Example
Music
App
Let’s say we have been observing high user churn
in the music app. Now, we want to identify these
users in advance so that we could reach out to
users before they leave the app
How could you identify users who have high probability
to churn away from the app?
Music
App
Predictive Application by Example
SELECT e.unique_id,
Count(distinct session_id)
FROM events e
WHERE event_type = ‘_session.start’
HAVING e.date> GETDATE() - 30
You can start by looking at
usage patterns of all users in the
last 30 days
One Way To Do is…
SELECT e.unique_id,
Count(distinct session_id)
FROM events e
WHERE event_type = ‘_session.start’
AND
date_part (dow,e.date ) in (6,7)
HAVING e.date> GETDATE() - 30
But usage pattern changes on
weekends.
You can edit the query to filter
for weekends only
One Way To Do is…
SELECT e.unique_id,
Count(distinct session_id)
FROM events e
WHERE event_type = ‘_session.start’
AND
date_part (dow,e.date ) in (6,7)
HAVING e.date> GETDATE() - 60
Pattern is not clear. You can go
back in time to get a more clear
pattern
One Way To Do is…
SELECT e.unique_id,
Count(distinct session_id),
e.music_genre , e.subscription_type ,
e.locale
FROM events e
WHERE event_type = ‘_session.start’
AND
date_part (dow,e.date ) in (6,7)
HAVING e.date> GETDATE() - 60
You want to learn not only from
usage data but from custom
behavior in the app
One Way To Do is…
SELECT e.unique_id,
Count(distinct session_id),
e.music_genre , e.subscription_type ,
e.locale
FROM events e
WHERE event_type = ‘_session.start’
AND
date_part (dow,e.date ) in (6,7)
HAVING e.date> GETDATE() - 120
….and again
One Way To Do is…
SELECT e.unique_id, Count(distinct session_id)
, e.music_genre , e.subscription_type , e.locale
FROM events e
WHERE event_type = ‘_session.start’
AND date_part (dow,e.date ) in (6,7)
HAVING e.date> GETDATE() - 120
Use machine learning technology to
learn business rules from your data
Machine learning automatically finds patterns
in your data and uses them to make predictions
Better Way To Do it is…
Users with High
probability to churn
Users with Low
probability to churn
Machine learning automatically finds patterns
in your data and uses them to make predictions
Your data + Machine Learning
Predictive applications in the app
Better Way To Do it is…
Users with High
probability to churn
Users with Low
probability to churn
Amazon Mobile Analytics Amazon Machine Learning
Leverage Mobile App Data to Build Predictive
Applications Using Amazon ML
Trainmodel
Evaluate andoptimize
Retrieve predictions
Building Predictive Applications with Amazon ML
1 2 3
Predict users with low probability to purchase in the app and send discount coupon
via in-app notification
Predict users with high probability to churn from the app and send push them
notification to re-engage
Identify users with high probability to share the app and reach out to them to do
the same
Recommend relevant content to users based on similar user’s behavioral
patterns
A Few Examples of Leveraging Mobile App
Data with Machine Learning
Amazon Mobile
Analytics
Amazon
Redshift
App events
InsightsStrategies
Predictions
Mobile app
developer Amazon Machine
Learning
+
Now Build Predictive Applications Using Your
Mobile App Data Easily
Your
Mobile
App
QuickSight
+
Getting Started:
Add Mobile Analytics to your app
1. Visit the AWS Mobile Hub
• Add “App Analytics” to your project
• Download your iOS or Android Source Code
2. Visit the Amazon Mobile Analytics console
• View out-of-the-box dashboards
• Turn on Auto-Export to get raw events in S3 and Redshift