Loading presentation...

Present Remotely

Send the link below via email or IM


Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.


Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Data Mining - Blue Book for Bulldozers (16:9)

No description

Will Cvengros

on 5 March 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Data Mining - Blue Book for Bulldozers (16:9)

Blue Book for Bulldozers Constantino Cervantes
William Cvengros
Jason Riebel
Michael Wintrode Auctioneers Sellers -
Contractors, Dealers, & Liquidators Buyers -
Construction Contractors Used Construction Equipment Goal

Tools Auction Price Prediction

Past Auction Data

Market Data

Data Modeling Past Auction Data

Market Data Past Auction Data All Variables
(53) Base Description (11)
Equipment Type
Model Condition (3)
Hours Operated
Usage Compared to Average Options (33)
Accessory Attachments Market (4)
Date of Sale
Sales Location
Auctioneer Output (1)
Sale Price World Price of Steel Index

Construction & Mining Machinery Manufacturer Revenue

Construction Equipment Wholesaler Revenue

US Values of Private Residential & Nonresidential Construction

CPI Inflation Data Preparation Original Data from

412,000+ Lines Merge Appendix Files
with Matlab &
Eliminate Obvious

360,000+ Lines

Initial Model Results Wheel Loaders Only

66,000+ Lines Valid Machine-Hour
Entries & Significant
Manufacturers Only

9,700+ Lines Sales since 2004

8,800+ Lines

Final Data Set
for Modeling Motor Grader Skidsteer Loader Backhoe Loader Equipment Type Track Excavator Track Type Loader Wheel Loader Data Modeling Results
Multi-Linear Regression

K-Nearest Neighbors

Regression Tree

Ensemble Methods Modeling Results Interpretations & Insights Most Significant Variables

Relatively High RMS Error Value

73rd Percentile on Kaggle Additional Improvement Non-sequential data partitioning

More robust modeling software

More information on reason for sale

Additional modeling techniques Questions? K-Nearest Neighbors Multi-Linear Regression Regression Tree Modeling Results EM - Bagging EM - Boosting
Full transcript