predictive modeling competitions
Download
Skip this Video
Download Presentation
Predictive modeling competitions

Loading in 2 Seconds...

play fullscreen
1 / 29

Predictive modeling competitions - PowerPoint PPT Presentation


  • 115 Views
  • Uploaded on

Predictive modeling competitions. making data science a sport. Anthony Goldbloom CEO, Kaggle e-mail [email protected] twitter @antgoldbloom. Photo by mikebaird, www.flickr.com/photos/mikebaird. Motivation Why compete? How it works R on Kaggle

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'Predictive modeling competitions' - joella


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
predictive modeling competitions
Predictive modeling competitions

making data science a sport

Anthony Goldbloom

CEO, Kaggle

e-mail [email protected]

twitter @antgoldbloom

Photo by mikebaird, www.flickr.com/photos/mikebaird

slide2
Motivation
  • Why compete?
  • How it works
  • R on Kaggle
  • The Heritage Health Prize
slide3
Global competitions

Predicting HIV viral load

Competition closes 77%

1½ weeks 70.8%

State of the art 70%

slide4
Crowdsourcing

Mismatch between those with data andthose with the skills to analyse it

additional slides
Additional slides

Not MIT, not SAS … UoL?

slide7
Tourism Forecasting Competition

Forecast Error(MASE)

Existing model

Aug 9

2 weeks later

1 month later

Competition End

slide8
Chess Ratings Competition

Existing model (ELO)

Error Rate(RMSE)

Aug 4

1 month

later

2 months

later

Today

slide10
Users apply different techniques
  • neural networks
  • logistic regression
  • support vector machine
  • decision trees
  • ensemble methods
  • adaBoost
  • Bayesian networks
  • genetic algorithms
  • random forest
  • Monte Carlo methods
  • principal component analysis
  • Kalman filter
  • evolutionary fuzzy modeling
slide11
Motivation
  • Why compete?
  • How it works
  • R on Kaggle
  • The Heritage Health Prize
slide12
Why Participants Compete

2

1

More fun than Sudoku

Clean, Real world data

Professional Reputation & Experience

4

3

Interactions with experts in related fields

Prizes

slide13
Motivation
  • Why compete?
  • How it works
  • R on Kaggle
  • The Heritage Health Prize
slide15
Competition Mechanics

Competitions are judged on objective criteria

slide16
Motivation
  • Why compete?
  • How it works
  • R on Kaggle
  • The Heritage Health Prize
slide21
Motivation
  • Why compete?
  • How it works
  • R on Kaggle
  • The Heritage Health Prize
slide29
What could the world’s bestanalysts find in your data?

e-mail [email protected]

phone +61438400053

Photo by gidzy, www.flickr.com/photos/gidzy

ad