1 / 10

Media Metrix

Media Metrix. Simon Hangl. Motivation. Scenarios Want to measure reach of a page along properties Age Location Want to check popularity of business category Shopping In November In the USA Want to get statistics about business sector i.e. How much money was been made in online shopping

jlinda
Download Presentation

Media Metrix

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Media Metrix Simon Hangl

  2. Motivation • Scenarios • Want to measure reach of a page along properties • Age • Location • Want to check popularity of business category • Shopping • In November • In the USA • Want to get statistics about business sector • i.e. How much money was been made in online shopping • i.e. Did this market grow?

  3. Solution? MediaMetrix! • Framework for Measuring Web Traffic • Most used tool • Demographic Information about users • Provides Reports along several properties • Reports available for • 41 countries, 6 global regions, world wide totals • Big data source • Sophisticated Statistics under the hood (very precise)

  4. How does it work? • Using Samples • Data Collection • Calibration Panel • Recruit users to observe their internet behavior • Offline Recruiting (i.e. random digital dialing) • Distinct Panels for Work and Home • Enumeration Surveys • 1100 interviews per month • demographic information collected • RDD • Measuring • Collecting Demographic Information from users • Measuring EVERYTHING (also secured https connections – such as banking connections) • Why should somebody do that? (internet storage, security software, winning cash prizes) • Some people do not even know

  5. How does it work? (2) • Estimation of Universe • Enumeration Interviews and Calibration Panel used to remove bias • Weighting Algorithm • Recruitment open to everyone – might influence statistics • Some users might not be honest • Use statistics to compute appropriate weights for visits • Such that each segment of population is adequately represented

  6. Example • User statistics in November 2011 • Locations (Home, Work, University) • Type of pages (all, shopping, …) • Subtypes (i.e. shopping  Toys, Electronics,…) • Range of Advertisement • See example

  7. How precise is it?

  8. Extensions to Core Reports • Ad Metrix: Advertisement Success • qSearch: Search Behavior • Mobile Metrix: Mobile Traffic Statistics • Video Metrix: Data about video usage • Plan Metrix: Information about lifestyle, interests, preferred products,… of users

  9. Relation to OC Work • Problems to apply this • Reimplementation • Very high cost • 2006: 545 servers, 280 terabytes of data, 1100 interviews per month • Reuse • Granularity probably not high enough (20,000 online entities in database – not enough?)

  10. Sources • http://www.comscore.com/Products_Services/Product_Index/Media_Metrix_Suite/Media_Metrix_Core_Reports • http://www.comscore.com/ger/Products_Services/Product_Index/Media_Metrix_Suite • http://www.mmetrics.com/ger/Press_Events/Press_Releases/2011/12/comScore_Media_Metrix_Ranks_Top_50_U.S._Web_Properties_for_November_2011 • http://thearf-org-aux-assets.s3.amazonaws.com/downloads/research/comScore-RReview.pdf • http://en.wikipedia.org/wiki/ComScore

More Related