Data Mining & Classification

0.0(0)
Studied by 0 people
call kaiCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/29

flashcard set

Earn XP

Description and Tags

BA 260 Final Exam

30 Terms

1
New cards

Supervised Learning

Uses known outcomes to predict outcomes for new cases.

2
New cards

Unsupervised Learning

Finds patterns or groups without a target outcome.

3
New cards

Data Preparation

Cleans, transforms, and organizes data before modeling.

4
New cards

Scatter Chart

Plots two variables to show their relationship.

5
New cards

Training Data

Data used to build the model.

6
New cards

Validation Data

Data used to tune or compare models.

7
New cards

Test Data

Held-back data used for a final performance check.

8
New cards

Overfitting

When a model fits training data well, but performs poorly on new data.

9
New cards

True Positive

Predicted positive; actually positive.

10
New cards

False Positive

Predicted Positive; actually negative.

11
New cards

True Negative

Predicted negative; actually negative.

12
New cards

False Negative

Predicted negative; actually postitive.

13
New cards

Sensitivity

Fraction of actual positives correctly identified:

TP/(TP+FN)

(recall)

14
New cards

Precision

Fraction of predicted positives that are truly positive:

TP/(TP+FP)

15
New cards

Accuracy

Fraction of predictions that are correct;

1 - error rate

16
New cards

Error Rate

Fraction of predictions that are incorrect.

17
New cards

Cuttoff Value

Probability threshold that turns a model’s score into a positive or negative prediction.

18
New cards

Lower Cutoff

Usually flags more positives, raising sensitivity and false positives.

19
New cards

Higher Cutoff

Usually flags fewer positives, reducing false positives, but potentially missing more actual positives.

20
New cards

Data Exploration

Uses summaries and visuals to understand data and patterns.

21
New cards

Supervised

A bank uses past loan records labeled “repaid” or “defaulted” to predict whether new applicants will default.

What learning is this?

22
New cards

Unsupervised

A store groups shoppers by similar shopping habits, without predicting a labeled outcome.

What learning is this?

23
New cards

Data Preparation

Correcting typos and handling missing values before modeling.

24
New cards

Data Exploration

Creating charts and summary statistics to understand the data.

25
New cards

TP/(TP+FN)

What is the formula for sensitivity?

26
New cards

TP/(TP+FP)

What is the formula for precision?

27
New cards

85%

A model’s error rate is 15%.

What is its accuracy?

28
New cards

More, Increases

If you lower the classification cutoff, does the model usually flag more cases or fewer cases as positive?

What usually happens to false positives?

29
New cards

Lower, Rises

A hospital wants to catch more patients who truly have a disease and can accept extra false alarms.

Should it raise or lower the cutoff?

What happens to sensitivity?

30
New cards