Important Questions: Introduction to Data Science
Section A (MCQ)
Focus on:
• Data Science Fundamentals
• Data Science lifecycle and project stages
• Roles of Data Scientist and applications
• Data Security and privacy issues
• Data Collection strategies
• Data Cleaning
• Data Integration
• Data Reduction
• Data Transformation
• Data Discretization
• Descriptive Statistics (Mean, Median, Mode, Variance, Standard Deviation)
• Skewness and Kurtosis
• Box Plot, Heat Map, Pivot Table, Distribution Plot
• Correlation Statistics
• ANOVA
• Simple Regression
• Multiple Regression
• Polynomial Regression
• Residual Plots
• Pipelines
• Overfitting and Underfitting
• Cross Validation
• Ridge Regression
• Grid Search
• Generalization Error
• Out-of-Sample Evaluation
• Exploratory Data Analytics (EDA)
Section B (10 Marks)
Introduction to Data Science
Important Question 1
Explain the evolution of Data Science and discuss its applications in various fields.
Important Question 2
Define Data Science and explain the roles of a Data Scientist in modern organizations.
Important Question 3
Describe the stages involved in a Data Science project with suitable examples.
Data Collection and Preprocessing
Important Question 4
Explain different data collection strategies and preprocessing techniques.
Important Question 5
Discuss data cleaning, data integration and data transformation methods used in Data
Science.
Important Question 6
Discuss the concepts of data reduction and data discretization with examples.
Exploratory Data Analytics and Visualization
Important Question 7
Illustrate the use of descriptive statistics such as mean, standard deviation, skewness and
kurtosis in exploratory data analytics.
Important Question 8
Demonstrate the use of box plots, pivot tables and heat maps for data visualization.
Important Question 9
Explain the importance of exploratory data analytics in decision making.
Regression and Data Analysis
Important Question 10
Analyze the role of correlation statistics and ANOVA in data analysis.
Important Question 11
Compare simple regression and multiple regression models with suitable examples.
Important Question 12
Illustrate the implementation of simple and multiple regression models using suitable
datasets.
Important Question 13
Compare polynomial regression and ridge regression techniques.
Model Development and Evaluation
Important Question 14
Demonstrate the use of residual plots and distribution plots in model evaluation.
Important Question 15
Analyze the importance of prediction and decision making in model development.
Important Question 16
Explain pipelines and their role in model development.
Section C (15 Marks)
Important Long Questions
1. Evaluate the importance of model evaluation techniques such as cross validation and out-
of-sample evaluation metrics.
2. Critically analyze the problems of overfitting and underfitting in machine learning
models.
3. Evaluate the effectiveness of cross validation techniques in reducing model errors.
4. Critically examine the role of grid search in testing multiple model parameters.
5. Design a predictive analytics model using polynomial regression and pipelines.
6. Create a model selection framework using ridge regression and grid search techniques.
7. Design a complete data preprocessing pipeline for a real-world dataset.
8. Create a predictive model using regression techniques for business decision making.