PSS718 - Data Mining Policy and Strategy Studies Asst.Prof.Dr. - - PowerPoint PPT Presentation

pss718 data mining
SMART_READER_LITE
LIVE PREVIEW

PSS718 - Data Mining Policy and Strategy Studies Asst.Prof.Dr. - - PowerPoint PPT Presentation

PSS718 - Data Mining Policy and Strategy Studies Asst.Prof.Dr. Burkay Gen Hacettepe University September 26, 2016 Who Am I? Asst. Prof. Dr. Burkay Gen (Industrial Engineer, Computer Scientist) Institute of Population Studies Policy and


slide-1
SLIDE 1

PSS718 - Data Mining

Policy and Strategy Studies Asst.Prof.Dr. Burkay Genç

Hacettepe University

September 26, 2016

slide-2
SLIDE 2

Who Am I?

  • Asst. Prof. Dr. Burkay Genç

(Industrial Engineer, Computer Scientist) Institute of Population Studies Policy and Strategy Studies Computational Geometry, Game Technologies, Data Analysis, Social Networks

Asst.Prof.Dr. Burkay Genç PSS718 - Data Mining

slide-3
SLIDE 3

What is Data Mining?

Data Mining is the science of extracting information hidden in structured

  • r unstructured data. Data ususally comes dirty, noisy and unstructured.

We have to clean it, remove noise, and structure, so that we can process

  • it. Then, we can dive deep into the data to extract information out of it.

Figure: Steps of Data Mining

Asst.Prof.Dr. Burkay Genç PSS718 - Data Mining

slide-4
SLIDE 4

Why?

Determine relations in data Detect possible improvements Understand the system Model Predict

Asst.Prof.Dr. Burkay Genç PSS718 - Data Mining

slide-5
SLIDE 5

Course Identity

Course Name PSS718 Semester The. App. Credit ECTS Data Mining PSS718 G/B 3 3 10

Asst.Prof.Dr. Burkay Genç PSS718 - Data Mining

slide-6
SLIDE 6

Evaluation

Assignments (A): 2 or 3 assignments -> 50% Project or Final (P) -> 50% Overall (O) -> (A) + (P) -> 100% Opinion Grade (K)-> 0.8 - 1.2 Assigned Grade (G) -> (O) * (K) Pass Grade -> 60 What does that mean? O = 100 -> 80 - 100 O = 75 -> 60 - 90 O = 50 -> 40 - 60

Asst.Prof.Dr. Burkay Genç PSS718 - Data Mining

slide-7
SLIDE 7

Content

Content to be covered: Working with Data Loading Data Exploring Data Graphics Descriptive and Predictive Analytics Cluster Analysis Association Analysis Decision Trees Random Forests Boosting Support Vector Machines

Asst.Prof.Dr. Burkay Genç PSS718 - Data Mining

slide-8
SLIDE 8

Book and Resources

Data Mining with Rattle and R, Graham Williams, Springer The Web

Asst.Prof.Dr. Burkay Genç PSS718 - Data Mining

slide-9
SLIDE 9

Software

R: Free! -> https://www.r-project.org/ R-Studio: Free! -> https://www.rstudio.com/ Rattle: Free! -> Install in R-Studio

Asst.Prof.Dr. Burkay Genç PSS718 - Data Mining