Practice Lightgbm And Catboost (5.5) - Supervised Learning – Advanced Algorithms

Practice: LightGBM and CatBoost

Lesson 5.5Supervised Learning – Advanced Algorithms

Practise this section

9 questions

Flashcard drill
2 cards from this section. Quick, good the night before a test.
Exercise
6 questions · about 4 min · pass mark 70%. Hints available.
Sign up to start the exercise
Quiz
3 questions · about 2 min · pass mark 70%. Hints available.
Sign up to start the quiz

6 sample questions

Question 1.
What does LightGBM stand for?
Show hintHide hint
Think about its focus on speed and efficiency.
Question 2.
What type of data is CatBoost optimized for?
Show hintHide hint
Remember, it directly handles a certain type of feature.
3Question 3.
What type of tree growth does LightGBM use?
- Level-wise
- Leaf-wise
- Depth-wise
Show hintHide hint
Think about which approach is better for capturing complexities.
4Question 4.
True or False: CatBoost requires categorical features to be manually encoded before modeling.
- True
- False
Show hintHide hint
Remember its core advantage.
Question 5.
You have a dataset with millions of records, significantly containing categorical features. Which algorithm would you leverage and why? Elaborate on your choice comparing LightGBM and CatBoost.
Show hintHide hint
Think about what it takes to preprocess and the strengths of both algorithms.
Question 6.
If tasked with improving a current model that is overfitting, what strategies could be derived from CatBoost's methods that could also be applied to other models?
Show hintHide hint
Consider how controlled learning and validation might help.

5 more questions in this section. Enroll free to practise them all.