8.2 Predictive Analytics: Model Evaluation & Bias-Variance Trade-Off Flashcards

1
Q

What is the primary goal of supervised learning methods?

A

To minimize error by making predictions as accurate as possible.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

How do classification methods evaluate model accuracy?

A

By calculating the percentage of correct predictions.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

How do regression models measure error?

A

By calculating the difference between predicted and actual values.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Why is evaluating unsupervised learning models difficult?

A

We don’t have labeled data, so we don’t know the correct number of groups or classifications.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is the purpose of a train-test split in machine learning?

A

To evaluate how well a model generalizes to unseen data and prevent overly optimistic projections.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What percentage of data is typically used for training vs. testing?

A

80% for training, 20% for testing

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What happens at deployment after the train-test split?

A

The model is trained on 100% of the data based on what was learned during model evaluation.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is the formula for model error?

A

Model Error = Irreducible error + Bias + Variance

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is irreducible error in a model?

A

Noise in the data or insufficient data to fully represent patterns, which cannot be reduced by training models.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

How is bias measured in a model?

A

By how far predictions are from actual values; high bias means the model oversimplifies patterns.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

How is variance measured in a model?

A

By how much predictions fluctuate around the mean when trained on different data.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is underfitting?

A

When a model hasn’t sufficiently learned patterns from the data, leading to high bias and low variance.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is overfitting?

A

When a model fits too tightly to the training data, causing low bias and high variance.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is the ideal bias-variance trade-off?

A
  • Low bias and low variance
  • a model complex enough to capture patterns but not overly sensitive to small data changes.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

How do training error and variance relate?

A
  • As training error decreases, model complexity increases, leading to higher variance.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How do error rates indicate underfitting and overfitting?

A
  • Underfit model: High error in both training and testing data.
  • Overfit model: Low error in training but high error in testing