tag:blogger.com,1999:blog-5652924.post5271187554514151031..comments2024-03-02T01:02:21.655-08:00Comments on Applied Data Science and <br>Machine Learning: Predictive Analytics World, part 1Dean Abbotthttp://www.blogger.com/profile/16818000233889520746noreply@blogger.comBlogger3125tag:blogger.com,1999:blog-5652924.post-89697914381767584262009-11-08T10:06:30.039-08:002009-11-08T10:06:30.039-08:00Thanks for the feedback Dean. I hadn't the cha...Thanks for the feedback Dean. I hadn't the chance to attend this event, but I'm happy to read some info about it.Sandro Saittahttps://www.blogger.com/profile/17682082649770875583noreply@blogger.comtag:blogger.com,1999:blog-5652924.post-80169285721143971752009-11-02T17:58:26.790-08:002009-11-02T17:58:26.790-08:00For those interested, one of the first papers (I s...For those interested, one of the first papers (I saw) on the subject of incremental lift modeling is here: http://www.sigkdd.org/explorations/issues/4-2-2002-12/lo.pdf<br /><br />Portrait Software has tools dedicated to this as well: <br />http://www.portraitsoftware.com/Products/portrait_uplift_optimizerJeffhttps://www.blogger.com/profile/17017204540630564477noreply@blogger.comtag:blogger.com,1999:blog-5652924.post-12583004153869027342009-10-28T22:48:03.713-07:002009-10-28T22:48:03.713-07:00Hi Dean,
Your presentation made me an emsemble co...Hi Dean,<br /><br />Your presentation made me an emsemble convert! I previously hadn’t given ensembles much thought, but I was surprised that ensembles could provide robustness, or that a simple mathematical average would be used! (I thought some form of weighting would be the norm)<br /><br />I'm planning on testing a few ensembles next week. I’ll let you know who they go on large Tim Mannshttps://www.blogger.com/profile/17405266346372888597noreply@blogger.com