(mbl309) analyze mobile app data and build predictive applications

© 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

“If you can’t measure it, you can’t improve it”-Lord Kelvin

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


trends to know

what's happening in

the app


behavior to

enhance experience


behavior to shape


decisions

Let’s just say we have built a music app Music App

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


Collect, visualize, and export app usage data

Amazon Mobile Analytics“Collect, visualize and export your app usage data at scale”

Accurate results


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


Get started by visiting:

aws.amazon.com/mobileanalytics/


trends to know

what's happening in

the app


behavior to enhance

experience


behavior to shape


decisions


Going beyond standard metrics will give

you more insight in to user behavior

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

Auto Export to Amazon Redshift

Simple &

intuitive

Integrate with

existing data

models

Automatically

collect common

attributes

Schema for Your App’s Event Data

Now Easy to Query and Visualize

Your

Mobile

App

Now Easy to Query and Visualize

Your

Mobile

App

QuickSight

New

Introducing

Amazon QuickSight

Integration with BI Tools is Very Easy

Amazon QuickSight

Sign up for the preview:

aws.amazon.com/quicksight


trends to know

what's happening in

the app


behavior to enhance

experience


behavior to shape


decisions


Predicting user behavior helps in

delivering personalized

experiences for users

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,


FROM events e


AND

date_part (dow,e.date ) in (6,7)


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,


FROM events e


AND



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


AND



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


AND



….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


AND date_part (dow,e.date ) in (6,7)


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


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


Users with Low


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

Build Amazon ML Models with a Few Clicks

Explore Model Quality

Amazon Machine Learning

Get started by visiting:

aws.amazon.com/machine-learning/

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

Thank you!

Questions?

Reach us at:

[email protected]

Remember to complete

your evaluations!

(mbl309) analyze mobile app data and build predictive applications

Technology