1、eBay M2M Email Analysis on Hadoop Pla4orm ForestSu,DanielZhangOctober 2011 eBay Inc. Confiden.al TheBirthofeBay...StartedwithaBrokenLaserPointer...AuctionWebwasbornontheLaborDayweekendinSeptember1995$30eBayFounder...soldfor$14.83USDPierreOmidyareBay Inc.
3、rDay48BillionSQLCallsGlobalPresentsPerday2PetabytesIn33International5.5BillionAPICallsStoredMarketsPermonth25PetabytesProcesseddaily>4.4GBSourceCodeeBay Inc. Confiden.al 3 VelocityoftradingOnanaveragedayoneBay…ADiamondRingissoldeverytwominutes4Velocityof
6、LoadETLLoadStruDcutuarleLdoDaadtaUnstDruucatulrLeodaDdataDataFeedDualLoadUnstructuredDataKnowledgeTransactionalDatabasesFeedbackeBay Inc. Confiden.al 8 eBay Email Universe •Members write to each other (“M2M”) •Members write to eBay •eBay writes to Member
7、s ‐Millions of times per day! •Where are these messages? oIn My Messages: Messages through eBay oIn a user’s private system: Messages outside of eBay eBay Inc. Confiden.al 9 Single User Study •What does a typical user send / receive? •Follow a single use
8、r for 50 days during Oct/Nov 2010 •User ProNile: ―User subscribed to daily deal ―User was member of: eBay Bucks eBay VIP PayPal Advantage ―User is mainly a buyer but also a casual seller eBay Inc. Confiden.al 10 Single User Stu