The Curse of Big Data in Mobile Analytics Dr. Guodong (Gordon) Gao M-CERSI Workshop, 9/11/2015.

Slides:



Advertisements
Similar presentations
Presented by: Your Name Your Phone Number Your Website Address How Your Local Business Can ATTRACT and KEEP Customers Through Mobile Marketing.
Advertisements

Rebooting Our Faith: How cell phones, Facebook & text messages alter our fundamental operating system. Dr. Peggy Kendall Department of Communication Studies.
Print meets Web 2.0. Information sharing Interoperability User-centered design Collaboration Web 2.0.
Module 36: Correlation Pitfalls Effect Size and Correlations Larger sample sizes require a smaller correlation coefficient to reach statistical significance.
Big Data and Predictive Analytics in Health Care Presented by: Mehadi Sayed President and CEO, Clinisys EMR Inc.
Frank Yu Australian Bureau of Statistics Unstructured Data 1.
Exploring social media tools Melanie Moran Vanderbilt University SEC Communicators Association June 10, 2008.
Dr. Michael R. Hyman, NMSU Correlation (Click icon for audio)
Study Design Data. Types of studies Design of study determines whether: –an inference to the population can be made –causality can be inferred random.
Did You Know? Number of spam s sent each day? 100 billion.
Register for Patient Access today Beat the phone queue Online 24 hours a day Appointment booking Repeat prescriptions Free mobile app To register, just.
Social Media Marketing for your Small Business. phone: website:
Chantelle van der Merwe FORUM Credit Union Marketing Intern July 2011.
Trends in computing Rachael Vowden Wildern school
UFCFX5-15-3Mobile Device Development Commercial Trends and Competitive Initiatives.
Online Medical Advice Ryan & Raahem. Mobile Phones Mobile phones are common in rural area where internet is not Mobiles can be used to raise awareness.
+ The Future of Social Media By Abigail Boghurst.
1.3 Specialist Phones The aim of this Teaching Block is to encourage students to think about mobile phones – personal digital devices that they use every.
Mobile PD. Objectives  State of mobile ownership and use  Mobile technology with higher education students  Mobile technology with younger students.
DIABETES UK TRACKER SMARTPHONE APP 28 March #duktracker "This app is so focused and simple, yet it's ingenious. I loved the way they tested.
LRC320 SP12 Group 4 Presentation Project by: Frank Castro Jasmine Lee & German Lopez.
Social Media USE OF SOCIAL MEDIA BY CHILD HELPLINES.
Tennessee Technological University1 The Scientific Importance of Big Data Xia Li Tennessee Technological University.
GOOGLE TALK, TRANSLATE, VOICE Group #6: Michelle Nakamoto, Jennifer Morgan, Ashley Uhrin October 23, 2013 Westphal EDT321.
Rasheed Rabbi 1. Presentation Outline Research Goal Used example or case study Key Idea and Key words Health Care knowledge repository Questions 2.
A sensor for measuring the acceleration of a moving or vibrating body.
Sweets, Testing, and Communicating -- Katherine Bulman, Susan Jacob, Rishi Thakkar, and Soumya Vhasure.
©2012 STARWOOD HOTELS & RESORTS WORLDWIDE, INC. | Proprietary & Confidential AGE OF GREAT CHANGE IAMAI JUNE 2013 MUMBAI.
Telecommunication technology Then and Now. But First… What is telecommunication Technology? Telecommunication is the transmission of messages over a country.
Presented by: Your Name Your Phone Number Your Website Address How Mobile Apps Can Help You Connect With Local Consumers.
Mobile Social Networks
Chapter 2 Developmental Psychology A description of the general approach to behavior by developmental psychologists.
Generating and sharing large datasets: Moving out of our measurement comfort Rita Kukafka and Pamela M. Kato October 16-17, 2012 Bruxelles, Belgique.
Features of mobile apps. Introduction of mobile apps  FACEBOOK  Facebook is an online social networking service. Its name comes from a colloquialism.
Types of Ads. Right Column: The sidebar on the right hand side of the page at all times as you are using Facebook. Newsfeed: The 'homepage' on Facebook.
By: Kyra Alexander.  Bubble Inclinometer ◦ Measures Range of Motion using small Device. ◦ Price: $50- $140.
Review for Communication Unit Test Matching Short Answer Essay – 5 paragraph paper assignment.
Social Networking and Mobile Devices. What is social networking?
GO MOBILE By: Cindy Collins.  Some websites have what I call single serving content: you’ll go there once, and not return until you need it again.
What is Data Communication? Data communication is the process of collecting and distributing data(text, voice, graphics, video, etc) electrically from.
1 Unstructured Data (UD) What is unstructured data? How is it statistically valuable? Challenges of turning UD into information.
Today we are teaching the Millennial Generation!!!!
Facebook Messenger Presentation
The Future of Mobile Marketing Lee Mueller University of Montana Integrated Online Marketing 420.
Presenter: Ken Baldauf Web 2.0 Technologies for Educators.
App reviews By Meghan Roles. Introduction I am going to be talking about 2 different apps. One app is called Tripomatic, which is a city guide, and the.
Doc.: IEEE s Submission May 2016 Yuko Hirabe et al., NAISTSlide 1 Project: IEEE P Working Group for Wireless Personal Area Networks.
The graph shows how questions that I have asked the people around me. Every one that I asked has a cell phone and they text a lot. Most of them text a.
Technology Tips and Safety for Teens. Social Networks Social Networks are internet applications which are used to facilitate communication between users.
Leveraging Social Media Analytics to Protect the Brand, Improve Products and enhance Operational Performance Derive business value from unstructured data.
LAB OF THINGS Sam Stokes. LAB OF THINGS: STORING DATA FROM THINGS Check for your Device Get the toolsCommunity.
Experiments Textbook 4.2. Observational Study vs. Experiment Observational Studies observes individuals and measures variables of interest, but does not.
MEDIA KIT. WHO WE ARE? YOUR TEXT HERE 6:58 min AVG. SESSION DURATION 13.6M+ UNIQUE USERS 2.8M+ FACEBOOK LIKES 189M+ MONTHLY PAGE VIEWS 71.3M+ RETURNING.
How to stay safe using the internet & App’s
Facebook privacy policy
Annual Professional Development Conference
PhoneSheriff – Best Parental Control Software For Mobiles and Tablets
BIG Data 25 Need-to-Know Facts.
Personal Digital Devices Lesson 1
What this activity will show you
APPS are the next big thing Mobango
Google Hangouts Google Hangouts is a instant messaging service. Hangouts supports text, voice and video conversations, and is cross-platform on the.
Kim Chen Faculty Mentors: Dr. Pamela Wisniewski and Dr. Damla Turgut
Register for Patient Access today
Anonymous Reporting App
Sierra Hall Synergy Sports & Orthopedic Physical Therapy CEO
Skype.
Sample Analytics Categories
Anonymous Reporting App
Presentation transcript:

The Curse of Big Data in Mobile Analytics Dr. Guodong (Gordon) Gao M-CERSI Workshop, 9/11/2015

Mobile devices = Big Data  User generated data  Facebook ingests 500 terabytes of new data every day.  Text messages, diet log, photos, videos, …  System generated data  App download and usage  Gesture, touches  Communications with other wearable devices  Sensor-generated data  6 billion mobile phones  Geo-location data, pedometer, heart beat sensor, and oxygen saturation sensor 2

Even more data 3

7

5

6

Causal inference  Most the statistical methods try to measure correlations, not causation.  For actionable knowledge, we need causation!  Does the roster crowing cause the sun to rise?  Confusing correlation with causality can be dangerous 7

8

9

 Does Anne Hathaway help Warren Buffet get richer? 10

The curse of big data  Heterogeneity in Treatment Effects (HTE)  Sub-group analysis  Helps answer:  Which sub-group will benefit from this treatment?  Should I prescribe the treatment to this particular patient?  With dozens of variable, and thousands of combinations, we can define sub-group in many ways  e.g. 10 variables, each with 3 levels, there are 3^10 = 59,049 combinations!  We are doomed to find something statistically significant in certain sub-groups 11

Yet another curse of big data 12

Do not ignore the fundamentals  Patient #11 13