BEGIN:VCALENDAR
PRODID:NingEventWidget-v1
VERSION:2.0
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Pacific/Gambier
X-LIC-LOCATION:Pacific/Gambier
BEGIN:STANDARD
TZOFFSETFROM:-0900
TZOFFSETTO:-0900
TZNAME:GAMT
DTSTART:19700101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:6448529:Event:372759
DTSTAMP:20210228T194643Z
SUMMARY:Webinar Series: 3 Ways to Improve your Regression (Hands-on Co
mponent)
DESCRIPTION:Webinar Series: 3 Ways to Improve your Regression\nJanuary
20th and 27th, 10AM â€“ 11AM PT\n\nIf the time is inconvenient, pleas
e register and we will send you a recording.\n\nÂ \nClick to Register\
n\nAlternative Link: http://info.salford-systems.com/3-ways-to-improve
-your-regression-part1\n\nÂ \nAbstract:\n\nLinear regression plays a b
ig part in the everyday life of a data analyst, but the results arenâ€
™t always satisfactory.\nWhat if you could drastically improve predict
ion accuracy in your regression with a new model that handles missing
values, interactions, AND nonlinearities in your data?\nInstead of pro
ceeding with a mediocre analysis, join us for this 2-part webinar seri
es.Â \nWe will show you how modern algorithms can take your regression
model to the next level and expertly handle your modeling woes.\nYou
will walk away with several different methods to turn your ordinary re
gression into an extraordinary regression!\n\nThis webinar will be a s
tep-by-step presentation that you can repeat on your own! Â Included w
ith Registration:\n\nWebinar recording\n30 day software evaluation\nDa
taset used in presentation\nStep-by-step instruction for you to try at
home\n\nÂ \nWho should attend:\n\nAttend if you want to implement dat
a science techniques even without a data science, statistical or progr
amming background.\nAttend if you want to understand why data science
techniques are so important for forecasting.\n\nÂ \nClick to Register\
nAlternative Link: http://info.salford-systems.com/3-ways-to-improve-y
our-regression-part1\nÂ \nAgenda Part 1: January 20Â \n\nWe introduce
MARS nonlinear regression, TreeNet gradient boosting, and Random Fores
ts and show you how to extract actionable insight.\nTechniques:\nNonli
near regression splines (via MARS): this tool is ideal for users who p
refer results in a form similar to traditional regression while allowi
ng for bends, thresholds, and other departures from straight-line meth
ods.\nStochastic gradient boosting (via TreeNet): this flexible and po
werful data mining tool generates hundreds of decision trees in a sequ
ential, error-correcting process to produce an extremely accurate mode
l.\nRandom Forests: this method combines many decision trees independe
nt of each other and is best suited in analyses of small to moderate d
atasets.\n\n\n\nÂ \nAgenda Part 2: January 27\n\nWe will show you how
to take these techniques even further and take advantage of advanced m
odeling features.\nThere will be overlap with Part 1. It is recommende
d to watch Part 1, but not required.\nTechniques:\nStochastic gradient
boosting: TreeNet plots show you the impact of every variable in your
model; take it a step further by creating spline approximations to th
ese variables and using them in a conventional linear regression for a
boosted model performance!\nNonlinear regression splines: MARS nonlin
ear regression will still give you what looks like a standard regressi
on equation, but instead of coefficients, youâ€™ll see transformations
of your original variables.\nModeling automation: learn how to cycle
through numerous modeling scenarios automatically to discover best-fit
parameters.\n\n\n\nÂ \n\nFor more information visit https://www.datas
ciencecentral.com/events/webinar-series-3-ways-to-improve-your-regress
ion-hands-on-1
DTSTART;TZID=Pacific/Gambier:20160112T100000
DTEND;TZID=Pacific/Gambier:20160112T110000
CATEGORIES:webinar, 2-part, series
LOCATION:Online, on-demand
WEBSITE:http://hubs.ly/H01bfR30
URL:http://hubs.ly/H01bfR30
CONTACT:(619) 543-8880 x109
ORGANIZER;CN="Lisa Solomon":https://www.datasciencecentral.com/profile
/LisaSolomon
ATTACH;FMTTYPE="image/jpeg":
ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=ACCEPTED;RSVP=TRUE;CN="Lisa Sol
omon":https://www.datasciencecentral.com/profile/LisaSolomon
END:VEVENT
END:VCALENDAR