| Starts: | Sunday November 01, 2009 at 12:00pm |
|---|---|
| Ends: | Sunday November 01, 2009 at 7:30pm |
| Event Type: | Conference |
| Region: | San Francisco Bay Area |
| Location: |
Hackers Dojo S Whisman Rd Mountain View, CA 94041 US |
| Price: | |
| Website: | http://www.sfbayacm.org/?p=894 |
| Industry: | computer software |
| Keywords: | Acm, Data Mining, Cloud Computing, Machine Learning |
| Intended For: | C**, VP's, consultants, software developers, product managers, those who want their business dollars to go farther with analytics |
| Organization: | San Francisco Bay Area Association of Computing Machinery |
See the ACM site for full details, and to share topics you are interested in for the un-conference. Optional $20 to join the SF Bay ACM for the year.
POSSIBLE TOPICS that may be proposed: • Introduction to data mining, how to get started, FAQ • Challenges in vertical market X (internet advertising, medical, green tech, finance, marketing, retail, …) • Discuss algorithm X (Support Vector Machines, TreeNet, NaïveBayes, Clustering, outlier detection, text mining) • Bring your challenges to brainstorm on current projects with experts • Netflix $1,000,000 data mining competition, presentation of collaborative filtering papers by Yehuda Koren from Greg Makowski • New developments in R and the Windows IDE – presented by David of REvolution Computing • Problem identification - best customers/prod
GOLD SPONSOR: REvolution Computing - Open source products and servinces for high performance analytics. KXEN - Knowledge Extraction Engines - The leading provider of automated data mining software and customer analytic solutions. LinkedIn - Over 50 million professionals use LinkedIn to exchange information, ideas and opportunities
APPROXIMATE SCHEDULE 12:00 Arrive, name tags, network, brainstorm discussion topics with others, eat 12:45 Main session starts, overview of the day 1:00 Panel of experts answering questions from the audience 1:30 Gold Sponsor & Dojo presentations 1:50 Audience members line up to suggest discussion topics to the room. If a minimum threshold of people are interested in the topic, then it gets a discussion slot We can have 6+ concurrent discussion slots per time slot Recommend for each discussion a primary facilitator and a note taker to report at the end 2:30 Time Slot 1 (many concurrent sessions) 3:30 Time Slot 2 ( “ “ “ ) 4:30 Time Slot 3 5:30 Time Slot 4 6:30 Report summary of sessions over food & drinks in the main area, networking 7:30 Camp organizers invite any help in picking up after the free unconference
Mining healthcare data
I am proposing a health care topic too: Biomedical Data Mining: Dimensionality, Noise, Applications
I am using the LinkedIn site for the RSVP details, and the ACM site for the topic discussions. I would invite you to post your healthcare topics to http://www.sfbayacm.org/?p=894. Please share some details and any links to related reading people might feel interested in. THANKS FOR YOUR INTEREST!!
There are many areas in healthcare where data mining is critical. At present time, clinical data mining for decision making system, and machine learning on consumer health information are probably interesting to some people here. Healthcare search engine is also another exciting area.
I propose discussing algorithms X (Support Vector Machines, TreeNet, NaïveBayes, Clustering, outlier detection, text mining)
FYI. I am going to present a paper "A Brief Guide to Legal Issues for Data-miners" to the Bay Area SAS User group. You can find out more details in basas.com. Date: Thursday, October 29th, 2009 Time: 1:30pm-4:30pm Registration starts at 1:00pm Locations: Northern California Kaiser Permanente Division of Research 2000 Broadway Oakland, CA 94612
I'd like to hear discussions on dealing with highly imbalanced data (e.g., 0.1% density of successes in dataset. Also would be useful to discuss best practices and suitable models for datasets where most features are categorical rather than numerical.
I'm interesting in OSS tools that support data mining in production environments (live or near-real time). Otherwise I'm very interested in general overview and survey of the state-of-the-art.
I would like to discuss how to data mine without disturbing the existing systems. Too often the set of data applications is such a fine set of spaghetti that you do not want to disturb.
Hello, I would encourage all suggestions to get posted on http://www.sfbayacm.org/?p=894
Hi Aaron, I would be very interested in learning more about your researching pertaining to the legal issues with Data-mining. Where can I find the paper to read more? Please let me know, sukantag@gmail.com SG
AJ, I agree with you whole heartedly on the emphasis of data mining for health information. My emphasis is not in the clinical decision space but am aggressive about data mining for health care and health information for consumers directed towards Pervasive Health Care. MedgoLine is working on this and we do our best to stay stealth mode but nonetheless big from research point of view SG
Dr. Irene, Very interested in this area too. Unfortunately will miss the session today but am hoping the presentation and discussions can come online. SG
doesn't anyone have the link to the scribe notes (on etherpad) of the sparse-data talk? Thanks!
does*
It was an amazing event! There were more than 225 people in attendance. Thank you to everyone who attended! There is a blogs about the camp: General impression: http://www.zemanta.com/fruitblog/acm-data-mining-camp-silicon-valley-report/ Focus on R: http://bit.ly/3sM5kQ BioMedical: http://aurametrix.blogspot.com/2009/11/biomedical-data-mining-dimensionality.html There were many "tweets" about the camp People even put up a twitpics http://twitpic.com/nx57f http://tweetphoto.com/xbs1abje http://img682.yfrog.com/i/b07.jpg/ Here are some slides about the event! http://www.slideshare.net/clibou/datacamp