BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:(Research) Privacy Policies for the Individual / (Research) Traffi
 c Signal Data: Prediction using Machine Learning - Sören Preibusch and Us
 man Khan
DTSTART:20090209T140000Z
DTEND:20090209T150000Z
UID:TALK16998@talks.cam.ac.uk
CONTACT:Andrew Rice
DESCRIPTION:Research: Privacy Policies for the Individual\, Sören Preibus
 ch\n\nPrivacy policy negotiations allow individually tailored data process
 ing schemes on a per transaction basis. Mandatory data collection is repla
 ced by incentivised data revelation. Consumers are offered choices in priv
 acy-related decision-making\; and service providers can leverage customers
 ' privacy concerns and turn data protection from a business impediment int
 o a competitive advantage. The timing of data collection and the dimension
 ing of effective incentives are decision parameters in designing and imple
 menting successful privacy negotiations.\nOn Web sites with social network
 ing features\, privacy negotiations allow moderation of the quantity and q
 uality of information released\, including the topology of the social netw
 ork itself. Existing standards can be exploited to enable securely and sel
 ectively hidden friendship links in a distributed social networking scenar
 io.\nThis talk reviews the impact and design of privacy policy negotiation
 s in centralised and distributed architectures\, reports on ongoing work\,
  and sketches future research directions.\n\n\nResearch: Traffic Signal Da
 ta: Prediction using Machine Learning\, Usman Khan\n\nWe evaluate the accu
 racy of prediction of traffic signal data using a simple Decision Tree lea
 rning algorithm (a modification of the simple ID3 Decision Tree learning a
 lgorithm).\n
LOCATION:FW26\, William Gates Building
END:VEVENT
END:VCALENDAR