"Know your customers by knowing who they know, and who they don't" In the highly saturated and competitive mobile (cell-phone) industry, telecommunication companies continually seek new ways to analyse and understand customer behaviour. Whilst the priority of data mining analysis in the telecommunications industry is to retain customers, being able to successfully target customers for appropriate upgrades (for example, new handsets or higher priced plans) and additional value added services greatly enhances customer value. One recent development in Optus strategy for better customer insights is social network analysis (SNA). SNA is about understanding the social fabric of your customer base. What influences your customers and prospects to behave as they do? Tim Manns will present a case study of an in-house In-Database social networking analysis solution developed for the Optus consumer mobile customer base. This deployed data mining solution runs monthly, analysing every communication event made and received by mobile customers. The presentation will illustrate some of the practical data mining challenges of processing and transforming several billion rows of data warehouse transactional level data (call detail records) into summarised customer data within a practical timeframe. Business benefits and predictive modelling outcomes will also be presented. Introduction to Tim… Tim fell into data mining in 1999 where he worked for several years at SPSS (UK) as the global technical specialist for the data mining software Clementine. Since 2006 Tim has been a data miner for the Australian telecommunications provider Optus. He has developed a diverse range of in-database customer analysis, most recently identifying social groups from mobile (cell-phone) usage. Three questions I might ask myself; - How long did the whole project take to complete and what were the biggest difficulties? - It is a simple interpretation of Social Network Analysis. Why haven’t you used a solution from one of the major vendors (IBM, eXtract, SAS etc)? - What do you think will be the next biggest challenge in telco customer analytics? This event is proudly sponsored by SAS. www.sas.com Registration: Registration for this event is a MUST! Please RSVP either way! If you are able to join us on the night, we will have a printed name badge for you. Building Logistics: Google's Sydney office is on the 5th floor of a building that is owned by Accenture. The building doors close at 6pm each night, and they must be opened by someone with a building badge (i.e. a Googler). There are elevators and stairs that go up to the 5th floor, but the elevators also require a badge after 6pm. There will be 1 or 2 Googlers at the door from 5:45pm to let attendees in through the front door and badge them into the elevator. They will usually keep 1 person there about 15 minutes past the starting time, to check for stragglers. Location: Level 5, 48 Pirrama Street, Pyrmont, Sydney (View on Google Maps) Across from Star City casino. If the front door is closed and there is no Googler to let you in, please call Will Scully-Power on[masked] 866. Getting There: If you use the subway, you can go to Town Hall station and then walk across the Pyrmont footbridge. If you use the monorail, you can stop at the end of the footbridge, and walk from there. If you use the light rail, you can stop at the casino station and walk across the street. If you drive, then you can look for parking on the suburban streets around the office, and then walk from there. Time: We encourage all attendees to show up on time (5:45PM). If you have trouble getting in on the night please call Will Scully-Power on[masked] 866. Presentation Room: We will be in the Jumbuck room: seats around 50 comfortably. It's next to Google's game room, which they occasionally let visitors use. We will all be going to the (the Pyrmont Bridge Hotel) after the event for additional food, drinks & networking. I look forward to welcoming you on the night! Will Scully-Power Managing Director Datarati Pty Ltd Level 1, 111 Elizabeth Street Sydney, NSW 2000 Australia m: [masked] p: +61 (2)[masked] e: [masked] w: datarati.com.au t: twitter.com/willscullypower b: willscullypower.wordpress.com Datarati is a marketing analytics and optimisation company, providing digital advertising agencies, media agencies and their clients with actionable data driven insights which improve campaign performance and ROI.