In this Module 3 Discussion, we shall argue how to use R to precede logistic retrogradation on binary relative capricious datasets. Gladden counterpart the questions by swelling out the unmitigated on the lawful influence face of the board.
To counterpart these questions, gladden go balance the foul-mouthed patterns (Example 1,2,3,4) in Data Mining and Business Analytics delay R Chapter 7 and Data Mining for Business Analytics: Concepts, Techniques, and Applications in R Chapter 10 (all plant in this week's Readings & Resources) to perceive and then swell in the unmitigateds in the aloft board for R functions we can use to influencele those particular steps. You may so apply to some disclosed media to perceive applicable counterparts to swell in those unmitigateds as counterparts.
What are the percentages of the luxuriance and proof sets in those patterns?
What percentages do you conceive gain beget amend presage outcomes and why?
Describe what qualifies a good-tempered-tempered-tempered “lift curve”?
Do you conceive the “lift curve” for pattern 3 is a good-tempered-tempered-tempered one or not? Can you decipher why or why not?
What are the R functions we use to precede logistic retrogradation?
What are the automated capricious excerption heuristics we can use for optimal standard excerption in logistic and multiple retrogradations? Gladden so appearance as sundry R functions as you can.
Can you appearance how to compute the foresight reprove of evaluating the successes of presage in Board 10.8 of the applyence textbook (Ch. 10)?
In your reply to other students, allude-to changes to their counterparts that you conceive would perform it a stronger con-over, or ask clarifying questions if everything was privation or confusing.