-
1
Explain your notebook/project.
-
2
Explain the problem statement.
-
3
What approach did you follow to solve the problem?
-
4
What are the top insights from your EDA?
-
5
Explain every graph used in your EDA.
-
6
Why did you choose those plots?
-
7
How can you make your graphs cleaner?
-
8
What did you understand from the describe() output?
-
9
How did you correlate features with the target variable?
-
10
Why did you drop specific columns?
-
11
How did you identify and remove duplicates?
-
12
How did you handle missing values?
-
13
Why did you choose that imputation technique?
-
14
What preprocessing did you perform?
-
15
Why is preprocessing required?
-
16
What feature engineering did you perform?
-
17
Did you create any feature that improved your score significantly?
-
18
Did you create any feature that improved your score significantly?
-
19
How do lag features help?
-
20
How do rolling features help?
-
21
How did you implement lag and rolling features?
-
22
What is Backward Fill?
-
23
What is Forward Fill?
-
24
What encoding techniques did you use?
-
25
Explain One-Hot Encoding.
-
26
Explain Label Encoding.
-
27
Explain Ordinal Encoding.
-
28
Difference between One-Hot Encoding and Label Encoding.
-
29
When should you use Label Encoding?
-
30
What are the drawbacks of One-Hot Encoding?
-
31
What scaling techniques did you use?
-
32
Why is scaling required?
-
33
What happens if scaling is not applied?
-
34
How does StandardScaler work?
-
35
How does MinMaxScaler work?
-
36
Difference between StandardScaler and MinMaxScaler.
-
37
What is the range after applying StandardScaler?
-
38
What is the range after applying MinMaxScaler?
-
39
After applying StandardScaler, what are the new mean and standard deviation?
-
40
What percentage of values lie between -3σ and +3σ in a normal distribution?
-
41
Explain TF-IDF.
-
42
Why did you choose those models?
-
43
Explain the working of each model.
-
44
Explain Logistic Regression.
-
45
Explain the Sigmoid function.
-
46
Write the Sigmoid function formula.
-
47
How does Logistic Regression learn weights?
-
48
What is the loss function of Logistic Regression?
-
49
What changes are required for multiclass Logistic Regression?
-
50
Explain SVM.
-
51
SVM vs Logistic Regression for outliers.
-
52
Explain Decision Tree.
-
53
Explain Random Forest.
-
54
Explain Naive Bayes.
-
55
What are the limitations of Naive Bayes?
-
56
Explain XGBoost.
-
57
Explain LightGBM.
-
58
Difference between XGBoost and LightGBM.
-
59
Why is LightGBM better than other boosting algorithms?
-
60
Explain level-wise vs leaf-wise tree growth.
-
61
Explain Bagging.
-
62
Explain Boosting.
-
63
Which reduces bias and which reduces variance?
-
64
What is Gini Index?
-
65
What is Information Gain?
-
66
What is SMOTE?
-
67
Explain ROC Curve.
-
68
Explain Confusion Matrix.
-
69
What is hyperparameter tuning?
-
70
How does GridSearchCV work?
-
71
Why did you choose only those parameters/solvers for GridSearchCV?
-
72
How does Pipeline work?
-
73
What is overfitting?
-
74
How can you reduce overfitting?
-
75
How did you handle outliers?
-
76
How did you improve your model score?
-
77
How can you further improve model performance?
-
78
Why did you use R² score instead of Accuracy?
-
79
Explain ANOVA Test.
-
80
Explain Chi-Square Test.
-
81
What is PCA?
-
82
Explain the working of PCA.
-
83
What is multicollinearity?
-
84
How does Multiple Linear Regression work?
-
85
What is RFE?
-
86
How does RFE work?
-
87
How do you select important features from a dataset?
-
88
What feature extraction techniques have you used and why?
-
89
What are soft class predictions and hard class predictions?
-
90
Coding: Implement RFE to find the top 2 features.
-
91
Coding: Load the Breast Cancer dataset and find the top features using RFE.
-
92
Coding: Load the Diabetes dataset and find the top features using RFE.
-
93
Coding: Load the Iris dataset and use SelectKBest with Chi-Square to find the top 2 features.
-
94
Coding: Load the Iris dataset, train a Logistic Regression model with GridSearchCV, and print the classification report.
-
95
Coding: Generate a word cloud for each label/class separately.