-
1
Self introduction.
-
2
Explain the problem statement.
-
3
Explain your notebook to a non-technical person (e.g., your boss).
-
4
Abstract questions about the dataset (not technical).
-
5
Questions about college life.
-
6
How many models did you try?
-
7
How many models did you perform hyperparameter tuning on?
-
8
Why didn't you submit earlier?
-
9
Why F1 Score instead of Accuracy?
-
10
How is F1 Score calculated?
-
11
Macro vs Micro averaging.
-
12
Why only Accuracy was considered?
-
13
Did Hyperparameter Tuning improve your score?
-
14
Which is your baseline model?
-
15
What is imputation?
-
16
Why did you choose this imputation strategy?
-
17
What is scaling?
-
18
What is normalization?
-
19
What effect does normalization have on models?
-
20
What do you think about outliers in your dataset?
-
21
How did you handle class imbalance?
-
22
Explain Hyperparameter Tuning.
-
23
What did you do during Hyperparameter Tuning?
-
24
Why didn't you perform Hyperparameter Tuning? (if missing from notebook)
-
25
How much time did Hyperparameter Tuning take?
-
26
Loss function of Logistic Regression.
-
27
Loss function of Linear Regression.
-
28
Overfitting vs Underfitting.
-
29
How do you identify overfitting?
-
30
How do you overcome overfitting?
-
31
What is Cross Validation?
-
32
Pipeline.
-
33
PCA.
-
34
Regularization.
-
35
L1 vs L2 Penalty.
-
36
Explain how L1/L2 Regularization works.
-
37
Other ensemble models.
-
38
Boosting vs XGBoost vs LightGBM.
-
39
Explain how XGBoost works.
-
40
Explain how LightGBM works.
-
41
Can Gradient Boosting be converted into LightGBM?
-
42
Which was your best model?
-
43
Explain your best model in detail.
-
44
Advantages of your best model.
-
45
Difference between hstack() and vertical stacking (vstack()).
-
46
Difference between Seaborn and Matplotlib.
-
47
Load the Iris dataset.
-
48
Train a Logistic Regression model on it.
-
49
Self introduction
-
50
Problem statement explanation
-
51
Explain notebook to a non-technical person
-
52
Abstract questions on dataset
-
53
Questions about college life
-
54
How many models tried?
-
55
How many hyperparameter tuned?
-
56
Why didn't you submit earlier?
-
57
Why F1 instead of Accuracy?
-
58
F1 Score calculation
-
59
Macro vs Micro
-
60
Imputation
-
61
Imputation strategy
-
62
Scaling
-
63
Normalization and its effect
-
64
Outliers
-
65
Class imbalance handling
-
66
Hyperparameter tuning explanation
-
67
HPT improvement in score
-
68
HPT execution time
-
69
Logistic Regression loss function
-
70
Linear Regression loss function
-
71
Cross Validation
-
72
PCA
-
73
Pipeline
-
74
Regularization
-
75
L1 vs L2
-
76
Overfitting vs Underfitting
-
77
Detecting overfitting
-
78
Preventing overfitting
-
79
Boosting vs XGBoost vs LightGBM
-
80
LightGBM working
-
81
XGBoost working
-
82
Other ensemble models
-
83
Gradient Boosting → LightGBM conversion
-
84
Best model explanation
-
85
Advantages of best model
-
86
hstack vs vstack
-
87
Seaborn vs Matplotlib
-
88
Logistic Regression coding on Iris dataset